Check my GPU

Apple M2 Pro (32 GB) vs NVIDIA GeForce RTX 4090 for local AI

Pick two GPUs or Macs to see which runs more models, faster, for the kind of work you do.

Winner: NVIDIA GeForce RTX 4090

For general chat: Its ten best models average a score of 99 vs 93; it runs 32 more LLMs (439 vs 407); it is about 2.5× faster on its top models.

Side by side

  Apple M2 Pro (32 GB) NVIDIA GeForce RTX 4090
Memory 32.0 GB unified 24.0 GB VRAM
Usable for models 21.4 GB 24.0 GB
Memory bandwidth 200 GB/s 1,008 GB/s
FP16 compute 6.8 TFLOPS 82.6 TFLOPS
Launch price — $1,599
Released 2023 2022
LLMs that run 407 of 536 439 of 536
LLMs that run well 401 405
Image models that run 46 of 47 46 of 47
Video models that run 18 of 34 25 of 34
Top-10 LLM average score 93 99
Top-10 LLM average speed 40.0 tok/s 98.8 tok/s
Best LLM Gemma 4 26B-A4B Qwen3.8 27B

Highlighted values are the better of the two. Model results assume 8K of context and the default macOS GPU memory limit on Macs.

LLMs

Model Grade · points (Apple M2 Pro (32 GB)) Speed (Apple M2 Pro (32 GB)) Fit (Apple M2 Pro (32 GB)) Grade · points (NVIDIA GeForce RTX 4090) Speed (NVIDIA GeForce RTX 4090) Fit (NVIDIA GeForce RTX 4090)
Gemma 4 26B-A4BGoogle · 26B (3.8B active) 96 ptsExcellent (S) · 96 of 100 points: Model quality 39.5/45, Memory fit 24.0/25, Speed 12.5/15, Memory use 15.0/15, workload match +5.0 27.8 tok/s Tight fit 100 ptsExcellent (S) · 100 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 113 tok/s Tight fit
Qwen3.6 35B-A3BAlibaba · 36B (3.0B active) 94 ptsExcellent (S) · 94 of 100 points: Model quality 35.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 98 ptsExcellent (S) · 98 of 100 points: Model quality 40.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Qwen3.5 35B-A3BAlibaba · 36B (3.0B active) 94 ptsExcellent (S) · 94 of 100 points: Model quality 35.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 98 ptsExcellent (S) · 98 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active) 93 ptsExcellent (S) · 93 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Runs well 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active) 93 ptsExcellent (S) · 93 of 100 points: Model quality 34.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 97 ptsExcellent (S) · 97 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active) 92 ptsExcellent (S) · 92 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 97 ptsExcellent (S) · 97 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active) 92 ptsExcellent (S) · 92 of 100 points: Model quality 33.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 97 ptsExcellent (S) · 97 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Agents-A1 35B-A3BInternScience · 35B (3.0B active) 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active) 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Tight fit 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Qwen3.8 27BAlibaba · 28B 91 ptsExcellent (S) · 91 of 100 points: Model quality 40.9/45, Memory fit 24.0/25, Speed 6.5/15, Memory use 15.0/15, workload match +5.0 7.6 tok/s Tight fit 100 ptsExcellent (S) · 100 of 100 points: Model quality 41.7/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15, workload match +5.0 36.8 tok/s Tight fit
Qwen3.6 27BAlibaba · 28B 90 ptsExcellent (S) · 90 of 100 points: Model quality 40.2/45, Memory fit 24.0/25, Speed 6.5/15, Memory use 15.0/15, workload match +5.0 7.6 tok/s Tight fit 100 ptsExcellent (S) · 100 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 44.5 tok/s Runs well
Qwen3.5 27BAlibaba · 28B 90 ptsExcellent (S) · 90 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 6.5/15, Memory use 15.0/15, workload match +5.0 7.6 tok/s Tight fit 99 ptsExcellent (S) · 99 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 44.5 tok/s Runs well
gpt-oss 20BOpenAI · 21B (3.6B active) 89 ptsExcellent (S) · 89 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 13.3/15, Memory use 15.0/15, workload match +5.0 31.4 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15, workload match +5.0 184 tok/s Runs well
DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active) 89 ptsExcellent (S) · 89 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 26.4 tok/s Tight fit 93 ptsExcellent (S) · 93 of 100 points: Model quality 34.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 107 tok/s Tight fit
Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active) 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.4 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 187 tok/s Tight fit
TMax 27BAi2 · 27B 89 ptsExcellent (S) · 89 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.7 tok/s Tight fit 98 ptsExcellent (S) · 98 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.2 tok/s Runs well
Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active) 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 15.0/15, workload match +5.0 39.0 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 177 tok/s Tight fit
Fara 1.5 27BMicrosoft · 27B 88 ptsExcellent (S) · 88 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.7 tok/s Tight fit 97 ptsExcellent (S) · 97 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.2 tok/s Runs well
Qwen3 30B-A3BAlibaba · 31B (3.3B active) 87 ptsExcellent (S) · 87 of 100 points: Model quality 28.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.4 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 187 tok/s Tight fit
Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active) 87 ptsExcellent (S) · 87 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.4 tok/s Tight fit 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 187 tok/s Tight fit
UI-Mate 27BTencent · 27B 87 ptsExcellent (S) · 87 of 100 points: Model quality 36.8/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.7 tok/s Tight fit 96 ptsExcellent (S) · 96 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.2 tok/s Runs well
North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active) 87 ptsExcellent (S) · 87 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 14.1/15, Memory use 15.0/15 35.2 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 34.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 170 tok/s Tight fit
Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active) 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.6 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 206 tok/s Tight fit
Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active) 86 ptsExcellent (S) · 86 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.4 tok/s Tight fit 90 ptsExcellent (S) · 90 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 187 tok/s Tight fit
Gemma 4 12BGoogle · 12B 86 ptsExcellent (S) · 86 of 100 points: Model quality 35.5/45, Memory fit 25.0/25, Speed 10.0/15, Memory use 11.1/15, workload match +5.0 17.7 tok/s Runs well 96 ptsExcellent (S) · 96 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15, workload match +5.0 52.7 tok/s Runs well
ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active) 86 ptsExcellent (S) · 86 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 15.0/15, workload match +5.0 35.2 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 143 tok/s Runs well
Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active) 86 ptsExcellent (S) · 86 of 100 points: Model quality 28.2/45, Memory fit 24.0/25, Speed 14.1/15, Memory use 15.0/15, workload match +5.0 35.2 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 143 tok/s Tight fit
Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active) 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.4 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 242 tok/s Runs well
Sarvam 30BSarvam AI · 32B (2.4B active) 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 56.9 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 258 tok/s Tight fit
Gemma 4 31BGoogle · 31B 85 ptsExcellent (S) · 85 of 100 points: Model quality 34.4/45, Memory fit 24.0/25, Speed 7.0/15, Memory use 15.0/15, workload match +5.0 8.7 tok/s Tight fit 97 ptsExcellent (S) · 97 of 100 points: Model quality 38.9/45, Memory fit 24.0/25, Speed 14.9/15, Memory use 15.0/15, workload match +5.0 39.6 tok/s Tight fit
Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active) 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.2/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 15.0/15 39.0 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 177 tok/s Tight fit
Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active) 84 ptsGreat (A) · 84 of 100 points: Model quality 31.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 45.6 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 206 tok/s Tight fit
Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active) 84 ptsGreat (A) · 84 of 100 points: Model quality 29.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 41.4 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 187 tok/s Tight fit
Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active) 84 ptsGreat (A) · 84 of 100 points: Model quality 29.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 41.4 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 187 tok/s Tight fit
ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active) 84 ptsGreat (A) · 84 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 15.0/15 35.2 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 143 tok/s Runs well
LFM2 24B-A2BLiquid AI · 24B (2.3B active) 83 ptsGreat (A) · 83 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 46.0 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 24.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 222 tok/s Runs well
Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active) 83 ptsGreat (A) · 83 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15, workload match +5.0 41.4 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 112 tok/s Runs well
Apriel 1.5 15B ThinkerServiceNow · 15B 83 ptsGreat (A) · 83 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 14.0/15, workload match +5.0 14.2 tok/s Runs well 92 ptsExcellent (S) · 92 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.4 tok/s Runs well
Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active) 83 ptsGreat (A) · 83 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 13.5/15, workload match +5.0 35.2 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 105 tok/s Runs well
Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active) 83 ptsGreat (A) · 83 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 52.4 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 225 tok/s Runs well
Ornith 1.5 9BDeepReinforce · 9.7B 83 ptsGreat (A) · 83 of 100 points: Model quality 32.9/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 9.1/15, workload match +5.0 21.9 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 65.3 tok/s Runs well
Phi-4 Reasoning Vision 15BMicrosoft · 15B 83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 14.2/15, workload match +5.0 14.0 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.7 tok/s Runs well
Qwen3.5 9BAlibaba · 9.7B 82 ptsGreat (A) · 82 of 100 points: Model quality 32.5/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 9.1/15, workload match +5.0 21.9 tok/s Runs well 91 ptsExcellent (S) · 91 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 65.3 tok/s Runs well
Ornith 1.0 9BDeepReinforce · 9.7B 82 ptsGreat (A) · 82 of 100 points: Model quality 32.1/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 9.1/15, workload match +5.0 21.9 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 33.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 65.3 tok/s Runs well
Magistral Small 2507Mistral AI · 24B 82 ptsGreat (A) · 82 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.4 tok/s Runs well
TMax 9BAi2 · 9.0B 81 ptsGreat (A) · 81 of 100 points: Model quality 31.6/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 8.7/15, workload match +5.0 23.6 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15, workload match +5.0 70.4 tok/s Runs well
Qwen3 14BAlibaba · 15B 81 ptsGreat (A) · 81 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.7/15, workload match +5.0 14.3 tok/s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
EXAONE 4.5 33BLG AI Research · 34B 81 ptsGreat (A) · 81 of 100 points: Model quality 31.0/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15, workload match +5.0 8.0 tok/s Tight fit 93 ptsExcellent (S) · 93 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15, workload match +5.0 36.0 tok/s Tight fit
Gemma 3 27B ITGoogle · 27B 81 ptsGreat (A) · 81 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.7 tok/s Tight fit 90 ptsExcellent (S) · 90 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.2 tok/s Runs well
Magistral Small 2506Mistral AI · 24B 81 ptsGreat (A) · 81 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.4 tok/s Runs well
Hermes 4 14BNous Research · 15B 80 ptsGreat (A) · 80 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.6/15, workload match +5.0 14.3 tok/s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
MedGemma 27B Text ITGoogle · 27B 80 ptsGreat (A) · 80 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.8 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.8 tok/s Runs well
Granite 4.2 8BIBM · 8.8B 80 ptsGreat (A) · 80 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.7/15, workload match +5.0 24.1 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15, workload match +5.0 71.7 tok/s Runs well
InternVL3 14BShanghai AI Lab · 15B 80 ptsGreat (A) · 80 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 14.2/15, workload match +5.0 14.0 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.7 tok/s Runs well
Phi-4 (14B)Microsoft · 15B 80 ptsGreat (A) · 80 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15, workload match +5.0 14.4 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.9 tok/s Runs well
Qwen3-VL 32B InstructAlibaba · 33B 80 ptsGreat (A) · 80 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.2 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.0 tok/s Runs well
Mistral Small 3.2 24BMistral AI · 24B 80 ptsGreat (A) · 80 of 100 points: Model quality 29.1/45, Memory fit 24.0/25, Speed 7.0/15, Memory use 15.0/15, workload match +5.0 8.8 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
Granite 4.2 30BIBM · 29B 79 ptsGreat (A) · 79 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 7.2/15, Memory use 15.0/15, workload match +5.0 9.3 tok/s Tight fit 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.3 tok/s Tight fit
Ministral 3 14BMistral AI · 14B 79 ptsGreat (A) · 79 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 13.1/15, workload match +5.0 15.2 tok/s Runs well 88 ptsExcellent (S) · 88 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.2 tok/s Runs well
Qwen3 32BAlibaba · 33B 79 ptsGreat (A) · 79 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.3 tok/s Tight fit 91 ptsExcellent (S) · 91 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15, workload match +5.0 37.7 tok/s Tight fit
Mistral Small 3 24B (2501)Mistral AI · 24B 79 ptsGreat (A) · 79 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.4 tok/s Runs well
Qwen2.5 14B InstructAlibaba · 15B 79 ptsGreat (A) · 79 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15, workload match +5.0 14.4 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.9 tok/s Runs well
Mistral Small 3.1 24BMistral AI · 24B 79 ptsGreat (A) · 79 of 100 points: Model quality 28.2/45, Memory fit 24.0/25, Speed 7.0/15, Memory use 15.0/15, workload match +5.0 8.8 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
Gemma 4 E4BGoogle · 8.0B 79 ptsGreat (A) · 79 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 7.9/15, workload match +5.0 26.4 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15, workload match +5.0 78.7 tok/s Runs well
Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active) 78 ptsGreat (A) · 78 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 13.5/15, workload match +5.0 35.2 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 105 tok/s Runs well
GLM-4 32B 0414Zhipu AI · 33B 78 ptsGreat (A) · 78 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.4 tok/s Tight fit 90 ptsExcellent (S) · 90 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15, workload match +5.0 38.0 tok/s Tight fit
Phi-4 Reasoning Plus (14B)Microsoft · 15B 78 ptsGreat (A) · 78 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.4 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.0 tok/s Runs well
Devstral Small 2 (24B)Mistral AI · 24B 78 ptsGreat (A) · 78 of 100 points: Model quality 33.2/45, Memory fit 24.0/25, Speed 6.4/15, Memory use 15.0/15 7.3 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
Qwen2.5 14B Instruct 1MAlibaba · 15B 78 ptsGreat (A) · 78 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15, workload match +5.0 14.3 tok/s Runs well 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
Granite 4.1 30BIBM · 29B 78 ptsGreat (A) · 78 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 7.3/15, Memory use 15.0/15, workload match +5.0 9.5 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.9 tok/s Tight fit
LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active) 78 ptsGreat (A) · 78 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15, workload match +5.0 48.9 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 96.8 tok/s Runs well
EXAONE 4.0 32BLG AI Research · 32B 78 ptsGreat (A) · 78 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.5 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15, workload match +5.0 38.7 tok/s Tight fit
Olmo 3.1 32B InstructAi2 · 32B 78 ptsGreat (A) · 78 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.5 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15, workload match +5.0 38.4 tok/s Tight fit
Solar Pro Preview 22BUpstage · 22B 77 ptsGreat (A) · 77 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 15.0/15, workload match +5.0 9.5 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 46.2 tok/s Runs well
Qwen3.5 4BAlibaba · 4.7B 77 ptsGreat (A) · 77 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 6.3/15, workload match +5.0 37.5 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 62.3 tok/s Runs well
Phi-4 Reasoning (14B)Microsoft · 15B 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.4 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.0 tok/s Runs well
Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24B 77 ptsGreat (A) · 77 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.4 tok/s Runs well
InternVL3.5 8BShanghai AI Lab · 8.5B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 9.4/15, workload match +5.0 24.8 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15, workload match +5.0 73.8 tok/s Runs well
Qwen3-VL 8B InstructAlibaba · 8.8B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.6/15, workload match +5.0 24.1 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 71.8 tok/s Runs well
TMax 4BAi2 · 4.2B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15, workload match +5.0 41.5 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15, workload match +5.0 69.0 tok/s Runs well
Dolphin Mistral 24B Venice EditionCognitive Computations · 24B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 7.0/15, Memory use 15.0/15, workload match +5.0 8.8 tok/s Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.6 tok/s Runs well
Voxtral Small 24BMistral AI · 24B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 7.0/15, Memory use 15.0/15, workload match +5.0 8.7 tok/s Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.1 tok/s Runs well
Gemma 4 E2BGoogle · 5.1B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 41.3 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15, workload match +5.0 56.7 tok/s Runs well
Baichuan M2 32BBaichuan · 33B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.3 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15, workload match +5.0 37.8 tok/s Tight fit
Qwen2.5 32B InstructAlibaba · 33B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.3 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15, workload match +5.0 37.7 tok/s Tight fit
Agents-A1 4BInternScience · 4.5B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 6.3/15, workload match +5.0 38.5 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15, workload match +5.0 63.9 tok/s Runs well
Gemma 2 27B ITGoogle · 27B 77 ptsGreat (A) · 77 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 6.6/15, Memory use 15.0/15, workload match +5.0 7.8 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.5 tok/s Runs well
Devstral Small 1.1 (24B)Mistral AI · 24B 77 ptsGreat (A) · 77 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15 9.0 tok/s Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.4 tok/s Runs well
Granite 4.1 8BIBM · 8.8B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.7/15, workload match +5.0 24.1 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15, workload match +5.0 71.7 tok/s Runs well
Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active) 76 ptsGreat (A) · 76 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 13.2/15, workload match +5.0 35.2 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 105 tok/s Runs well
Qwen3 8BAlibaba · 8.2B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 9.2/15, workload match +5.0 25.8 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15, workload match +5.0 76.9 tok/s Runs well
MiniCPM-V 4.5 8BOpenBMB · 8.7B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 11.7/15, Memory use 9.5/15, workload match +5.0 24.3 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 72.4 tok/s Runs well
Magistral Small 1.2 (24B)Mistral AI · 24B 76 ptsGreat (A) · 76 of 100 points: Model quality 31.4/45, Memory fit 24.0/25, Speed 6.4/15, Memory use 15.0/15 7.3 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 31.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
Gemma 3 12B ITGoogle · 12B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 11.2/15, workload match +5.0 17.3 tok/s Runs well 86 ptsExcellent (S) · 86 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15, workload match +5.0 51.6 tok/s Runs well
Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active) 76 ptsGreat (A) · 76 of 100 points: Model quality 23.4/45, Memory fit 24.0/25, Speed 9.2/15, Memory use 15.0/15, workload match +5.0 15.2 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 68.7 tok/s Tight fit
Seed-OSS 36B InstructByteDance · 36B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.2/45, Memory fit 24.0/25, Speed 7.4/15, Memory use 15.0/15, workload match +5.0 9.6 tok/s Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 30.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 44.2 tok/s Tight fit
Qwen2.5-VL 32B InstructAlibaba · 33B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.2 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 47.8 tok/s Runs well
Fara 1.5 4BMicrosoft · 4.5B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.3/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 6.3/15, workload match +5.0 38.5 tok/s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15, workload match +5.0 63.9 tok/s Runs well
Apriel Nemotron 15B ThinkerServiceNow · 15B 76 ptsGreat (A) · 76 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 14.1/15 14.1 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.1 tok/s Runs well
Hermes 4.3 36BNous Research · 36B 76 ptsGreat (A) · 76 of 100 points: Model quality 24.9/45, Memory fit 24.0/25, Speed 7.4/15, Memory use 15.0/15, workload match +5.0 9.6 tok/s Tight fit 88 ptsExcellent (S) · 88 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 44.2 tok/s Tight fit
AceReason Nemotron 14BNVIDIA · 15B 76 ptsGreat (A) · 76 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.3 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
OpenReasoning Nemotron 14BNVIDIA · 15B 76 ptsGreat (A) · 76 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.3 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
Qwen2.5 Coder 14B InstructAlibaba · 15B 76 ptsGreat (A) · 76 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.3 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
GLM-4.1V 9B ThinkingZhipu AI · 10B 76 ptsGreat (A) · 76 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 9.6/15, workload match +5.0 20.5 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15, workload match +5.0 61.2 tok/s Runs well
MiMo-VL 7B RLXiaomi · 8.3B 76 ptsGreat (A) · 76 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 9.2/15, workload match +5.0 25.4 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15, workload match +5.0 75.8 tok/s Runs well
Mage-VL 4.7BMicrosoft · 4.7B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15, workload match +5.0 44.6 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15, workload match +5.0 61.2 tok/s Runs well
Reka Flash 3.1 (21B)Reka AI · 21B 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 7.5/15, Memory use 15.0/15 10.1 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 41.1 tok/s Runs well
Nemotron Nano 9B v2NVIDIA · 8.9B 75 ptsGreat (A) · 75 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 8.5/15, workload match +5.0 23.8 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 70.9 tok/s Runs well
Qwen3-VL 4B InstructAlibaba · 4.4B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.2/15, workload match +5.0 39.3 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15, workload match +5.0 65.4 tok/s Runs well
Ministral 3 14B ReasoningMistral AI · 14B 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 13.1/15 15.2 tok/s Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 45.2 tok/s Runs well
Qwen3 4B Instruct 2507Alibaba · 4.0B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15, workload match +5.0 43.4 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 72.2 tok/s Runs well
Mistral Small 22B (2409)Mistral AI · 22B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 15.0/15, workload match +5.0 9.5 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.9 tok/s Runs well
QwQ 32BAlibaba · 33B 75 ptsGreat (A) · 75 of 100 points: Model quality 29.5/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.3 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.8 tok/s Tight fit
Devstral Small 2505Mistral AI · 24B 75 ptsGreat (A) · 75 of 100 points: Model quality 28.2/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 15.0/15 9.0 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.4 tok/s Runs well
DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active) 75 ptsGreat (A) · 75 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.1/15 44.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 131 tok/s Runs well
Granite 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active) 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15, workload match +5.0 53.8 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 145 tok/s Runs well
DeepCoder 14B PreviewAgentica · 15B 75 ptsGreat (A) · 75 of 100 points: Model quality 27.4/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.3 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active) 75 ptsGreat (A) · 75 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.1/15, workload match +5.0 44.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 131 tok/s Runs well
UI-Mate 9BTencent · 9.4B 75 ptsGreat (A) · 75 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15 22.5 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15 66.9 tok/s Runs well
UI-Venus 2 9BAnt Group (inclusionAI) · 9.4B 75 ptsGreat (A) · 75 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15 22.5 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15 66.9 tok/s Runs well
InternVL3.5 38BShanghai AI Lab · 38B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.9/45, Memory fit 24.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.7 tok/s Tight fit
Ministral 3 8BMistral AI · 8.9B 75 ptsGreat (A) · 75 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 11.5/15, Memory use 9.6/15, workload match +5.0 23.7 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.9/15, workload match +5.0 70.6 tok/s Runs well
Falcon-H1 34B InstructTII · 34B 74 ptsGreat (A) · 74 of 100 points: Model quality 24.2/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.1 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 27.4/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15, workload match +5.0 36.8 tok/s Tight fit
Olmo 3.1 32B ThinkAi2 · 32B 74 ptsGreat (A) · 74 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.5 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15 38.4 tok/s Tight fit
Granite 4.2 3BIBM · 3.7B 74 ptsGreat (A) · 74 of 100 points: Model quality 23.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15, workload match +5.0 40.1 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.4/15, workload match +5.0 79.3 tok/s Runs well
OpenReasoning Nemotron 32BNVIDIA · 33B 74 ptsGreat (A) · 74 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.3 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.8 tok/s Tight fit
Skywork OR1 32BSkywork · 33B 74 ptsGreat (A) · 74 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.3 tok/s Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.8 tok/s Tight fit
DeepSeek R1 Distill Qwen 14BDeepSeek · 15B 74 ptsGreat (A) · 74 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.9/15 14.3 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
InternVL3 8BShanghai AI Lab · 7.9B 74 ptsGreat (A) · 74 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.2/15, workload match +5.0 26.6 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 79.3 tok/s Runs well
Command R (08-2024) 32BCohere · 32B 74 ptsGreat (A) · 74 of 100 points: Model quality 23.4/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.5 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15, workload match +5.0 38.3 tok/s Tight fit
Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0B 74 ptsGreat (A) · 74 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
InternLM2.5 20B ChatShanghai AI Lab · 20B 74 ptsGreat (A) · 74 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15, workload match +5.0 10.6 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.2 tok/s Runs well
JanusCoder 14BShanghai AI Lab · 15B 74 ptsGreat (A) · 74 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.6/15 14.3 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.6 tok/s Runs well
Mistral Nemo 12B InstructMistral AI · 12B 74 ptsGreat (A) · 74 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 11.9/15, workload match +5.0 17.3 tok/s Runs well 83 ptsGreat (A) · 83 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 51.6 tok/s Runs well
EXAONE Deep 32BLG AI Research · 32B 73 ptsGreat (A) · 73 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.5 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15 38.7 tok/s Tight fit
GLM-Z1 32B (0414)Zhipu AI · 33B 73 ptsGreat (A) · 73 of 100 points: Model quality 28.0/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.4 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 38.0 tok/s Tight fit
Codestral 22BMistral AI · 22B 73 ptsGreat (A) · 73 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 7.3/15, Memory use 15.0/15 9.5 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 45.9 tok/s Runs well
Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active) 73 ptsGreat (A) · 73 of 100 points: Model quality 17.6/45, Memory fit 24.0/25, Speed 12.2/15, Memory use 15.0/15, workload match +5.0 26.3 tok/s Tight fit 80 ptsGreat (A) · 80 of 100 points: Model quality 21.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 121 tok/s Tight fit
Qwen3 4BAlibaba · 4.0B 73 ptsGreat (A) · 73 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15, workload match +5.0 43.4 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 72.2 tok/s Runs well
Falcon 3 10B InstructTII · 10B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 10.7/15, workload match +5.0 20.5 tok/s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15, workload match +5.0 61.1 tok/s Runs well
OLMo 2 32B InstructAi2 · 32B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.5 tok/s Tight fit 84 ptsGreat (A) · 84 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15, workload match +5.0 38.4 tok/s Tight fit
Aya Expanse 32BCohere · 32B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.5 tok/s Tight fit 84 ptsGreat (A) · 84 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15, workload match +5.0 38.3 tok/s Tight fit
Aya Vision 32BCohere · 33B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.7/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.2 tok/s Tight fit 84 ptsGreat (A) · 84 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15, workload match +5.0 37.3 tok/s Tight fit
Hunyuan 7B InstructTencent · 7.5B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 12.6/15, Memory use 8.6/15, workload match +5.0 28.2 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15, workload match +5.0 84.0 tok/s Runs well
MiniCPM4 8BOpenBMB · 8.2B 73 ptsGreat (A) · 73 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 8.2/15, workload match +5.0 25.8 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 76.9 tok/s Runs well
Pixtral 12B (2409)Mistral AI · 12B 73 ptsGreat (A) · 73 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 9.8/15, Memory use 12.1/15, workload match +5.0 17.0 tok/s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 50.8 tok/s Runs well
InternVL3 38BShanghai AI Lab · 38B 73 ptsGreat (A) · 73 of 100 points: Model quality 22.1/45, Memory fit 24.0/25, Speed 7.1/15, Memory use 15.0/15, workload match +5.0 9.0 tok/s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.7 tok/s Tight fit
OLMo 2 13B InstructAi2 · 14B 73 ptsGreat (A) · 73 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 9.3/15, Memory use 15.0/15, workload match +5.0 15.4 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.9 tok/s Runs well
DeepSeek R1 Distill Qwen 32BDeepSeek · 33B 73 ptsGreat (A) · 73 of 100 points: Model quality 27.2/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15 8.3 tok/s Tight fit 84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.7 tok/s Tight fit
Olmo 3 7B InstructAi2 · 7.3B 73 ptsGreat (A) · 73 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 8.9/15, workload match +5.0 29.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 86.3 tok/s Runs well
Gemma 2 9B ITGoogle · 9.2B 73 ptsGreat (A) · 73 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 10.3/15, workload match +5.0 22.9 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15, workload match +5.0 68.2 tok/s Runs well
DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2B 72 ptsGreat (A) · 72 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 9.2/15 25.8 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 76.9 tok/s Runs well
Qwen2.5 7B InstructAlibaba · 7.6B 72 ptsGreat (A) · 72 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15, workload match +5.0 27.7 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15, workload match +5.0 82.7 tok/s Runs well
Qwen2.5-VL 7B InstructAlibaba · 8.3B 72 ptsGreat (A) · 72 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 8.4/15, workload match +5.0 25.5 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 76.0 tok/s Runs well
MiniCPM-o 2.6 8BOpenBMB · 8.7B 72 ptsGreat (A) · 72 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 11.7/15, Memory use 8.7/15, workload match +5.0 24.4 tok/s Runs well 79 ptsGreat (A) · 79 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 72.7 tok/s Runs well
GLM-4 9B 0414Zhipu AI · 9.4B 72 ptsGreat (A) · 72 of 100 points: Model quality 22.2/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15, workload match +5.0 22.5 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15, workload match +5.0 67.0 tok/s Runs well
Nemotron 3 Nano 4BNVIDIA · 4.0B 72 ptsGreat (A) · 72 of 100 points: Model quality 21.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 44.0 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15, workload match +5.0 73.1 tok/s Runs well
InternVL2.5 8BShanghai AI Lab · 8.1B 72 ptsGreat (A) · 72 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.0/15, workload match +5.0 26.2 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 78.0 tok/s Runs well
Phi-3 Medium 128K InstructMicrosoft · 14B 72 ptsGreat (A) · 72 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 13.5/15, workload match +5.0 15.1 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.1 tok/s Runs well
OpenHands LM 32BAll Hands AI · 33B 72 ptsGreat (A) · 72 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.3 tok/s Tight fit 83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.8 tok/s Tight fit
LFM2 8B-A1BLiquid AI · 8.3B (1.5B active) 71 ptsGood (B) · 71 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15, workload match +5.0 48.9 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 96.8 tok/s Runs well
Qwen2.5 7B Instruct 1MAlibaba · 7.6B 71 ptsGood (B) · 71 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15, workload match +5.0 27.7 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15, workload match +5.0 82.7 tok/s Runs well
Phi-3.5 Mini InstructMicrosoft · 3.8B 71 ptsGood (B) · 71 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 9.3/15, workload match +5.0 38.4 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15, workload match +5.0 76.0 tok/s Runs well
Falcon-H1 7B InstructTII · 7.6B 71 ptsGood (B) · 71 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 7.9/15, workload match +5.0 27.9 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15, workload match +5.0 83.0 tok/s Runs well
Granite 4.1 3BIBM · 3.4B 71 ptsGood (B) · 71 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 43.1 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15, workload match +5.0 85.4 tok/s Runs well
InternLM3 8B InstructShanghai AI Lab · 8.8B 71 ptsGood (B) · 71 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 8.7/15, workload match +5.0 24.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15, workload match +5.0 71.6 tok/s Runs well
Hermes 3 (Llama 3.1 8B)Nous Research · 8.0B 71 ptsGood (B) · 71 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Llama 3.1 8B InstructMeta · 8.0B 71 ptsGood (B) · 71 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Phi-3 Medium (14B)Microsoft · 14B 71 ptsGood (B) · 71 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 12.6/15, workload match +5.0 15.1 tok/s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.1 tok/s Runs well
Qwen3 4B Thinking 2507Alibaba · 4.0B 71 ptsGood (B) · 71 of 100 points: Model quality 24.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.9/15 43.4 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 72.2 tok/s Runs well
Phi-4 Mini (3.8B)Microsoft · 3.8B 71 ptsGood (B) · 71 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.0/15, workload match +5.0 38.2 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15, workload match +5.0 75.6 tok/s Runs well
Qwen2.5 Coder 32B InstructAlibaba · 33B 71 ptsGood (B) · 71 of 100 points: Model quality 25.3/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15 8.3 tok/s Tight fit 82 ptsGreat (A) · 82 of 100 points: Model quality 28.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.7 tok/s Tight fit
GLM-4 9B Chat 1MZhipu AI · 9.5B 71 ptsGood (B) · 71 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.4/15, workload match +5.0 22.3 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15, workload match +5.0 66.4 tok/s Runs well
North Micro VisionCohere · 2.5B 71 ptsGood (B) · 71 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15, workload match +5.0 43.4 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.4/15, workload match +5.0 117 tok/s Runs well
Ministral 3 3BMistral AI · 3.9B 71 ptsGood (B) · 71 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 6.8/15, workload match +5.0 38.1 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15, workload match +5.0 75.4 tok/s Runs well
Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5B 71 ptsGood (B) · 71 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 7.1/15, workload match +5.0 38.7 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15, workload match +5.0 64.4 tok/s Runs well
Granite 3.2 8B InstructIBM · 8.2B 71 ptsGood (B) · 71 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.3/15, workload match +5.0 25.9 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15, workload match +5.0 77.1 tok/s Runs well
Granite 3.3 8BIBM · 8.2B 71 ptsGood (B) · 71 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.3/15, workload match +5.0 25.9 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15, workload match +5.0 77.1 tok/s Runs well
MiniCPM-V 2.6 8BOpenBMB · 8.1B 70 ptsGood (B) · 70 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 8.3/15, workload match +5.0 26.1 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15, workload match +5.0 77.8 tok/s Runs well
Ministral 8B (2410)Mistral AI · 8.0B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 9.1/15, workload match +5.0 26.4 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15, workload match +5.0 78.5 tok/s Runs well
Seed-Coder 8B ReasoningByteDance · 8.3B 70 ptsGood (B) · 70 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 9.1/15 25.6 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 76.4 tok/s Runs well
QwQ 32B PreviewAlibaba · 33B 70 ptsGood (B) · 70 of 100 points: Model quality 24.9/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15 8.3 tok/s Tight fit 81 ptsGreat (A) · 81 of 100 points: Model quality 28.2/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15 37.8 tok/s Tight fit
GLM-4 9B Chat (2024)Zhipu AI · 9.4B 70 ptsGood (B) · 70 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15, workload match +5.0 22.5 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15, workload match +5.0 67.0 tok/s Runs well
EXAONE 3.5 7.8BLG AI Research · 7.8B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 8.8/15, workload match +5.0 27.0 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15, workload match +5.0 80.6 tok/s Runs well
DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Tülu 3 8BAi2 · 8.0B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Phi-4 Multimodal InstructMicrosoft · 5.6B 70 ptsGood (B) · 70 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.3/15, workload match +5.0 38.0 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15, workload match +5.0 52.1 tok/s Runs well
Phi-3.5 Vision InstructMicrosoft · 4.2B 70 ptsGood (B) · 70 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.1/15, workload match +5.0 42.1 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.8/15, workload match +5.0 70.0 tok/s Runs well
Apertus v1.5 8BSwiss AI · 8.9B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.5/15, workload match +5.0 23.8 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15, workload match +5.0 70.8 tok/s Runs well
InternLM2 Chat 20BShanghai AI Lab · 20B 70 ptsGood (B) · 70 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15, workload match +5.0 10.6 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.2 tok/s Runs well
Falcon 3 7B InstructTII · 7.5B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.6/15, Memory use 8.4/15, workload match +5.0 28.3 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15, workload match +5.0 84.4 tok/s Runs well
Gemma 3 4B ITGoogle · 4.3B 70 ptsGood (B) · 70 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15, workload match +5.0 40.6 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15, workload match +5.0 67.5 tok/s Runs well
LFM2.5 2.6BLiquid AI · 2.7B 70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 39.9 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15, workload match +5.0 108 tok/s Runs well
Hunyuan 4B InstructTencent · 4.2B 70 ptsGood (B) · 70 of 100 points: Model quality 18.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15, workload match +5.0 41.4 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 68.8 tok/s Runs well
MedGemma 4B ITGoogle · 4.3B 70 ptsGood (B) · 70 of 100 points: Model quality 19.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15, workload match +5.0 40.6 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15, workload match +5.0 67.5 tok/s Runs well
Qwen2.5-Omni 7BAlibaba · 11B 70 ptsGood (B) · 70 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 10.0/15, workload match +5.0 19.7 tok/s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.1/15, workload match +5.0 58.7 tok/s Runs well
MiMo 7B RLXiaomi · 7.8B 70 ptsGood (B) · 70 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 8.9/15 27.0 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15 80.4 tok/s Runs well
Granite 3.1 8B InstructIBM · 8.2B 70 ptsGood (B) · 70 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.3/15, workload match +5.0 25.9 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15, workload match +5.0 77.1 tok/s Runs well
GLM-Z1 9B (0414)Zhipu AI · 9.4B 70 ptsGood (B) · 70 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15 22.5 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15 67.0 tok/s Runs well
Phi-3 Mini 128K InstructMicrosoft · 3.8B 70 ptsGood (B) · 70 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 9.3/15, workload match +5.0 38.4 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15, workload match +5.0 76.0 tok/s Runs well
EXAONE Deep 7.8BLG AI Research · 7.8B 70 ptsGood (B) · 70 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 8.8/15 27.0 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 80.6 tok/s Runs well
Seed-Coder 8B InstructByteDance · 8.3B 70 ptsGood (B) · 70 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 9.1/15 25.6 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15 76.4 tok/s Runs well
Phi-3 Small 8K InstructMicrosoft · 7.4B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.5/15, workload match +5.0 28.6 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 85.2 tok/s Runs well
LFM2.5-VL 3BLiquid AI · 3.1B 69 ptsGood (B) · 69 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15, workload match +5.0 47.0 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15, workload match +5.0 93.0 tok/s Runs well
DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active) 69 ptsGood (B) · 69 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 14.3/15, workload match +5.0 37.8 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 112 tok/s Runs well
Jamba Reasoning 3BAI21 Labs · 3.2B 69 ptsGood (B) · 69 of 100 points: Model quality 19.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15, workload match +5.0 45.8 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15, workload match +5.0 90.7 tok/s Runs well
Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Hermes 2 Pro Llama 3 8BNous Research · 8.0B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
OpenChat 3.6 8BOpenChat · 8.0B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
InternVL2 8BShanghai AI Lab · 8.1B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 9.0/15, workload match +5.0 26.2 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 78.0 tok/s Runs well
Gemma 3n E4BGoogle · 7.9B 69 ptsGood (B) · 69 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 7.8/15, workload match +5.0 26.9 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15, workload match +5.0 80.2 tok/s Runs well
Olmo 3 7B ThinkAi2 · 7.3B 69 ptsGood (B) · 69 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 8.9/15 29.0 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 86.3 tok/s Runs well
Yi 1.5 34B Chat01.AI · 34B 69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15, workload match +5.0 7.9 tok/s Tight fit 79 ptsGreat (A) · 79 of 100 points: Model quality 21.4/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15, workload match +5.0 36.0 tok/s Tight fit
SmolLM3 3BHugging Face · 3.1B 69 ptsGood (B) · 69 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 47.6 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15, workload match +5.0 94.3 tok/s Runs well
Llama 3.2 11B Vision InstructMeta · 11B 69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 10.6/15, Memory use 10.9/15, workload match +5.0 19.8 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15, workload match +5.0 59.0 tok/s Runs well
Falcon-H1R 7BTII · 7.6B 69 ptsGood (B) · 69 of 100 points: Model quality 23.9/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 7.9/15 27.9 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15 83.0 tok/s Runs well
Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4B 69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 11.9/15, Memory use 9.5/15, workload match +5.0 25.1 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15, workload match +5.0 74.9 tok/s Runs well
Qwen2 7B InstructAlibaba · 7.6B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15, workload match +5.0 27.7 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15, workload match +5.0 82.7 tok/s Runs well
Qwen2-VL 7B InstructAlibaba · 8.3B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 8.4/15, workload match +5.0 25.5 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 76.0 tok/s Runs well
Command R7BCohere · 8.0B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.2/15, workload match +5.0 26.3 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 78.4 tok/s Runs well
Aya Vision 8BCohere · 8.6B 69 ptsGood (B) · 69 of 100 points: Model quality 18.8/45, Memory fit 25.0/25, Speed 11.7/15, Memory use 8.6/15, workload match +5.0 24.5 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 73.0 tok/s Runs well
Llama 3 8B InstructMeta · 8.0B 69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Granite 4.0 Micro (3B)IBM · 3.4B 69 ptsGood (B) · 69 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 43.1 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15, workload match +5.0 85.4 tok/s Runs well
Qwen2.5 Coder 7B InstructAlibaba · 7.6B 69 ptsGood (B) · 69 of 100 points: Model quality 23.5/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15 27.7 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15 82.7 tok/s Runs well
Phi-3 Vision 128K InstructMicrosoft · 4.2B 68 ptsGood (B) · 68 of 100 points: Model quality 14.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.1/15, workload match +5.0 42.1 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.8/15, workload match +5.0 70.0 tok/s Runs well
Jamba2 3BAI21 Labs · 3.0B 68 ptsGood (B) · 68 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15, workload match +5.0 48.4 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15, workload match +5.0 95.8 tok/s Runs well
Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active) 68 ptsGood (B) · 68 of 100 points: Model quality 10.3/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 13.6/15, workload match +5.0 39.1 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 117 tok/s Runs well
Qwen1.5 14B ChatAlibaba · 14B 68 ptsGood (B) · 68 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 15.0/15, workload match +5.0 14.9 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 60.6 tok/s Runs well
OpenReasoning Nemotron 7BNVIDIA · 7.6B 68 ptsGood (B) · 68 of 100 points: Model quality 23.1/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15 27.7 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15 82.7 tok/s Runs well
Phi-3 Mini 4K InstructMicrosoft · 3.8B 68 ptsGood (B) · 68 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.6/15, workload match +5.0 38.4 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15, workload match +5.0 76.0 tok/s Runs well
Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active) 68 ptsGood (B) · 68 of 100 points: Model quality 23.3/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 49.2 tok/s Runs with offload 82 ptsGreat (A) · 82 of 100 points: Model quality 23.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 339 tok/s Tight fit
Command R7B ArabicCohere · 8.0B 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.2/15, workload match +5.0 26.3 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 78.4 tok/s Runs well
AFM 4.5BArcee AI · 4.6B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 45.8 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15, workload match +5.0 62.8 tok/s Runs well
CogVLM2 Llama 3 Chat 19BZhipu AI · 20B 68 ptsGood (B) · 68 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 8.9/15, Memory use 15.0/15, workload match +5.0 14.0 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 52.4 tok/s Runs well
InternLM2.5 7B ChatShanghai AI Lab · 7.7B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.4/15, Memory use 8.7/15, workload match +5.0 27.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15, workload match +5.0 81.4 tok/s Runs well
Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active) 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15 41.3 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 242 tok/s Runs well
Qwen3.5 2BAlibaba · 2.3B 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15, workload match +5.0 47.4 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 128 tok/s Runs well
Aya Expanse 8BCohere · 8.0B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Apertus 8B InstructSwiss AI · 8.1B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 78.2 tok/s Runs well
Nous Hermes 2 SOLAR 10.7BNous Research · 11B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 10.4/15, workload match +5.0 19.7 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15, workload match +5.0 58.7 tok/s Runs well
SOLAR 10.7B InstructUpstage · 11B 68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 10.5/15, Memory use 10.4/15, workload match +5.0 19.7 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15, workload match +5.0 58.7 tok/s Runs well
OLMo 2 7B InstructAi2 · 7.3B 67 ptsGood (B) · 67 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 9.6/15, workload match +5.0 29.0 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15, workload match +5.0 86.3 tok/s Runs well
TMax 2BAi2 · 1.9B 67 ptsGood (B) · 67 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15, workload match +5.0 57.2 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15, workload match +5.0 154 tok/s Runs well
Granite 3.0 8B InstructIBM · 8.2B 67 ptsGood (B) · 67 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 8.6/15, workload match +5.0 25.9 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15, workload match +5.0 77.1 tok/s Runs well
OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active) 67 ptsGood (B) · 67 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15, workload match +5.0 41.4 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 112 tok/s Runs well
Qwen1.5 32B ChatAlibaba · 33B 67 ptsGood (B) · 67 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 6.9/15, Memory use 15.0/15, workload match +5.0 8.4 tok/s Tight fit 77 ptsGreat (A) · 77 of 100 points: Model quality 18.8/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15, workload match +5.0 38.1 tok/s Tight fit
MiniCPM3 4BOpenBMB · 4.1B 67 ptsGood (B) · 67 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 42.9 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15, workload match +5.0 71.3 tok/s Runs well
DeepSeek R1 Distill Llama 8BDeepSeek · 8.0B 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15 26.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15 78.4 tok/s Runs well
Mistral 7B Instruct v0.3Mistral AI · 7.3B 67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 8.4/15, workload match +5.0 29.2 tok/s Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.0 tok/s Runs well
Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0B 67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Granite 4.0 H MicroIBM · 3.2B 67 ptsGood (B) · 67 of 100 points: Model quality 16.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15, workload match +5.0 46.0 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15, workload match +5.0 91.0 tok/s Runs well
LLaVA 1.6 34BLLaVA · 35B 67 ptsGood (B) · 67 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15, workload match +5.0 7.9 tok/s Tight fit 76 ptsGreat (A) · 76 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 46.0 tok/s Runs well
Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8B 67 ptsGood (B) · 67 of 100 points: Model quality 20.5/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 7.0/15 38.2 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15 75.6 tok/s Runs well
Qwen3-VL 2B InstructAlibaba · 2.1B 67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 50.5 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15, workload match +5.0 136 tok/s Runs well
Zamba2 7B InstructZyphra · 7.4B 67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.7/15, Memory use 8.1/15, workload match +5.0 28.7 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15, workload match +5.0 85.6 tok/s Runs well
Voxtral Mini 3BMistral AI · 4.7B 67 ptsGood (B) · 67 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15, workload match +5.0 45.2 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15, workload match +5.0 62.0 tok/s Runs well
Llama 3.2 3B InstructMeta · 3.2B 66 ptsGood (B) · 66 of 100 points: Model quality 15.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15, workload match +5.0 45.7 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15, workload match +5.0 90.4 tok/s Runs well
Fara 7BMicrosoft · 8.3B 66 ptsGood (B) · 66 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 12.0/15, Memory use 8.4/15 25.5 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15 76.0 tok/s Runs well
EXAONE 3.0 7.8B InstructLG AI Research · 7.8B 66 ptsGood (B) · 66 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 8.2/15, workload match +5.0 27.0 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15, workload match +5.0 80.6 tok/s Runs well
Hermes 2 Pro Mistral 7BNous Research · 7.2B 66 ptsGood (B) · 66 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 8.4/15, workload match +5.0 29.2 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Starling LM 7B BetaNexusflow · 7.2B 66 ptsGood (B) · 66 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 8.4/15, workload match +5.0 29.2 tok/s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Falcon-H1 3B InstructTII · 3.2B 66 ptsGood (B) · 66 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15, workload match +5.0 46.6 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15, workload match +5.0 92.2 tok/s Runs well
DeepSeek Prover V2 7BDeepSeek · 6.9B 66 ptsGood (B) · 66 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 13.1/15, Memory use 11.4/15 30.6 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.0 tok/s Runs well
Gemma 3n E2BGoogle · 5.4B 66 ptsGood (B) · 66 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 6.2/15, workload match +5.0 38.9 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15, workload match +5.0 53.4 tok/s Runs well
Falcon3 Mamba 7B InstructTII · 7.3B 66 ptsGood (B) · 66 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 7.3/15, workload match +5.0 29.1 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15, workload match +5.0 86.6 tok/s Runs well
Orca 2 13BMicrosoft · 13B 66 ptsGood (B) · 66 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 14.7/15, workload match +5.0 16.2 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.4 tok/s Runs well
Qwen2.5-VL 3B InstructAlibaba · 3.8B 66 ptsGood (B) · 66 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 6.1/15, workload match +5.0 39.1 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15, workload match +5.0 77.4 tok/s Runs well
LFM2 2.6BLiquid AI · 2.6B 65 ptsGood (B) · 65 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15, workload match +5.0 41.9 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15, workload match +5.0 113 tok/s Runs well
Yi 34B Chat01.AI · 34B 65 ptsGood (B) · 65 of 100 points: Model quality 15.1/45, Memory fit 24.0/25, Speed 6.7/15, Memory use 15.0/15, workload match +5.0 7.9 tok/s Tight fit 75 ptsGreat (A) · 75 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15, workload match +5.0 36.0 tok/s Tight fit
Yi 1.5 9B Chat01.AI · 8.8B 65 ptsGood (B) · 65 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 8.7/15, workload match +5.0 23.9 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15, workload match +5.0 71.3 tok/s Runs well
Qwen2.5 3B InstructAlibaba · 3.1B 65 ptsGood (B) · 65 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15, workload match +5.0 47.5 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15, workload match +5.0 93.9 tok/s Runs well
Aya 23 8BCohere · 8.0B 65 ptsGood (B) · 65 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 8.9/15, workload match +5.0 26.3 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15, workload match +5.0 78.4 tok/s Runs well
Hermes 3 Llama 3.2 3BNous Research · 3.2B 65 ptsGood (B) · 65 of 100 points: Model quality 14.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15, workload match +5.0 45.7 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15, workload match +5.0 90.4 tok/s Runs well
Baichuan 2 13B ChatBaichuan · 14B 65 ptsGood (B) · 65 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 15.0/15, workload match +5.0 15.2 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 45.3 tok/s Runs well
OpenChat 3.5 (0106)OpenChat · 7.2B 65 ptsGood (B) · 65 of 100 points: Model quality 13.2/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6B 65 ptsGood (B) · 65 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 8.0/15 27.7 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15 82.7 tok/s Runs well
Qwen1.5 7B ChatAlibaba · 7.7B 65 ptsGood (B) · 65 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 11.2/15, workload match +5.0 35.4 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15, workload match +5.0 81.6 tok/s Runs well
Gemma 1.1 7B ITGoogle · 8.5B 65 ptsGood (B) · 65 of 100 points: Model quality 10.6/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 11.0/15, workload match +5.0 32.0 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15, workload match +5.0 73.8 tok/s Runs well
CodeGeeX4 All 9BZhipu AI · 9.4B 64 ptsGood (B) · 64 of 100 points: Model quality 19.7/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 9.0/15 22.5 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15 67.0 tok/s Runs well
Mistral 7B Instruct v0.2Mistral AI · 7.2B 64 ptsGood (B) · 64 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Nous Hermes 2 Mistral 7B DPONous Research · 7.2B 64 ptsGood (B) · 64 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
OpenChat 3.5 (1210)OpenChat · 7.2B 64 ptsGood (B) · 64 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
InternLM2 Math Plus 20BShanghai AI Lab · 20B 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15 10.6 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.2 tok/s Runs well
Granite 3.2 2B InstructIBM · 2.5B 64 ptsGood (B) · 64 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15, workload match +5.0 42.5 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15, workload match +5.0 115 tok/s Runs well
Granite 3.3 2BIBM · 2.5B 64 ptsGood (B) · 64 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15, workload match +5.0 42.5 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15, workload match +5.0 115 tok/s Runs well
RecurrentGemma 9B ITGoogle · 9.6B 64 ptsGood (B) · 64 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.1/15, Memory use 8.9/15, workload match +5.0 22.0 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15, workload match +5.0 65.4 tok/s Runs well
LFM2.5 1.2B InstructLiquid AI · 1.2B 64 ptsGood (B) · 64 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15, workload match +5.0 42.4 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15, workload match +5.0 248 tok/s Runs well
Falcon 3 3B InstructTII · 3.2B 64 ptsGood (B) · 64 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15, workload match +5.0 45.4 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.7/15, workload match +5.0 89.9 tok/s Runs well
StarCoder2 15B InstructBigCode · 16B 64 ptsGood (B) · 64 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 13.7/15 13.2 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15 39.5 tok/s Runs well
EXAONE 3.5 2.4BLG AI Research · 2.4B 64 ptsGood (B) · 64 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 44.7 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15, workload match +5.0 120 tok/s Runs well
Qwen3 1.7BAlibaba · 2.0B 64 ptsGood (B) · 64 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15, workload match +5.0 53.0 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15, workload match +5.0 143 tok/s Runs well
Gemma 7B ITGoogle · 8.5B 64 ptsGood (B) · 64 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 11.0/15, workload match +5.0 32.0 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15, workload match +5.0 73.8 tok/s Runs well
OpenHermes 2.5 Mistral 7BTeknium · 7.2B 64 ptsGood (B) · 64 of 100 points: Model quality 12.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Starling LM 7B AlphaBerkeley · 7.2B 64 ptsGood (B) · 64 of 100 points: Model quality 12.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Qwen2.5-Omni 3BAlibaba · 5.5B 63 ptsGood (B) · 63 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 14.7/15, Memory use 6.5/15, workload match +5.0 38.2 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15, workload match +5.0 52.4 tok/s Runs well
Granite 3.1 2B InstructIBM · 2.5B 63 ptsGood (B) · 63 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15, workload match +5.0 42.5 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15, workload match +5.0 115 tok/s Runs well
Llama 2 13B ChatMeta · 13B 63 ptsGood (B) · 63 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 13.0/15, workload match +5.0 21.0 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.4 tok/s Runs well
Gemma 2 2BGoogle · 2.6B 63 ptsGood (B) · 63 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15, workload match +5.0 41.2 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15, workload match +5.0 111 tok/s Runs well
DeepSeek Coder 6.7B InstructDeepSeek · 6.7B 63 ptsGood (B) · 63 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 40.5 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.1 tok/s Runs well
CodeGemma 7BGoogle · 8.5B 63 ptsGood (B) · 63 of 100 points: Model quality 14.5/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 12.1/15 24.8 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15 73.8 tok/s Runs well
Mistral 7B Instruct v0.1Mistral AI · 7.2B 63 ptsGood (B) · 63 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
StableLM 2 12B ChatStability AI · 12B 63 ptsGood (B) · 63 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 9.9/15, Memory use 11.4/15, workload match +5.0 17.4 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15, workload match +5.0 51.9 tok/s Runs well
Granite Code 20B InstructIBM · 20B 63 ptsGood (B) · 63 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15 10.5 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 42.8 tok/s Runs well
EXAONE 4.0 1.2BLG AI Research · 1.3B 62 ptsGood (B) · 62 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 84.1 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15, workload match +5.0 227 tok/s Runs well
Yi Coder 9B Chat01.AI · 8.8B 62 ptsGood (B) · 62 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 9.2/15 23.9 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15 71.3 tok/s Runs well
Yi 1.5 6B Chat01.AI · 6.1B 62 ptsGood (B) · 62 of 100 points: Model quality 12.0/45, Memory fit 25.0/25, Speed 14.0/15, Memory use 6.8/15, workload match +5.0 34.9 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15, workload match +5.0 47.9 tok/s Runs well
Neural Chat 7B v3.3Intel · 7.2B 62 ptsGood (B) · 62 of 100 points: Model quality 10.6/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
SmolVLM2 2.2B InstructHugging Face · 2.3B 62 ptsGood (B) · 62 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15, workload match +5.0 47.8 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15, workload match +5.0 129 tok/s Runs well
Granite 3.0 2B InstructIBM · 2.6B 62 ptsGood (B) · 62 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 40.9 tok/s Runs well 63 ptsGood (B) · 63 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15, workload match +5.0 110 tok/s Runs well
LLaVA 1.6 Mistral 7BLLaVA · 7.6B 62 ptsGood (B) · 62 of 100 points: Model quality 10.6/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 7.6/15, workload match +5.0 36.1 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15, workload match +5.0 83.2 tok/s Runs well
Granite Vision 3.2 2BIBM · 3.0B 62 ptsGood (B) · 62 of 100 points: Model quality 11.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15, workload match +5.0 49.2 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15, workload match +5.0 97.4 tok/s Runs well
DeepSeek Coder 33B InstructDeepSeek · 33B 62 ptsGood (B) · 62 of 100 points: Model quality 16.6/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15 8.2 tok/s Tight fit 71 ptsGood (B) · 71 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 48.0 tok/s Runs well
Code Llama 13B InstructMeta · 13B 62 ptsGood (B) · 62 of 100 points: Model quality 12.8/45, Memory fit 25.0/25, Speed 9.6/15, Memory use 15.0/15 16.2 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 65.9 tok/s Runs well
Falcon Mamba 7B InstructTII · 7.3B 62 ptsGood (B) · 62 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 6.4/15, workload match +5.0 37.6 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15, workload match +5.0 86.6 tok/s Runs well
LLaVA 1.5 13BLLaVA · 13B 62 ptsGood (B) · 62 of 100 points: Model quality 8.3/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 13.1/15, workload match +5.0 20.5 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 47.2 tok/s Runs well
WizardLM 13B v1.2WizardLM · 13B 62 ptsGood (B) · 62 of 100 points: Model quality 8.3/45, Memory fit 25.0/25, Speed 10.9/15, Memory use 13.0/15, workload match +5.0 21.0 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.4 tok/s Runs well
SQLCoder 7B v2Defog · 6.7B 62 ptsGood (B) · 62 of 100 points: Model quality 11.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 40.5 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.1 tok/s Runs well
Zephyr 7B BetaHugging Face · 7.2B 61 ptsGood (B) · 61 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15, workload match +5.0 37.7 tok/s Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.1 tok/s Runs well
Granite 4.0 H 1BIBM · 1.5B 61 ptsGood (B) · 61 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15, workload match +5.0 73.7 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15, workload match +5.0 199 tok/s Runs well
LFM2 1.2BLiquid AI · 1.2B 61 ptsGood (B) · 61 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15, workload match +5.0 42.4 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15, workload match +5.0 248 tok/s Runs well
SmolVLM 2.2B InstructHugging Face · 2.3B 61 ptsGood (B) · 61 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15, workload match +5.0 47.8 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15, workload match +5.0 129 tok/s Runs well
Orca 2 7BMicrosoft · 6.7B 61 ptsGood (B) · 61 of 100 points: Model quality 8.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15, workload match +5.0 40.5 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.1 tok/s Runs well
Qwen2.5 Coder 3B InstructAlibaba · 3.1B 61 ptsGood (B) · 61 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 47.5 tok/s Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15 93.9 tok/s Runs well
Falcon-H1 1.5B InstructTII · 1.6B 61 ptsGood (B) · 61 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 69.4 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 187 tok/s Runs well
Qwen3.5 0.8BAlibaba · 0.9B 61 ptsGood (B) · 61 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 57.0 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15, workload match +5.0 334 tok/s Runs well
Qwen2-VL 2B InstructAlibaba · 2.2B 61 ptsGood (B) · 61 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.3/15, workload match +5.0 48.7 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 131 tok/s Runs well
StarCoder2 15B (base)BigCode · 16B 61 ptsGood (B) · 61 of 100 points: Model quality 13.7/45, Memory fit 25.0/25, Speed 8.6/15, Memory use 13.7/15 13.2 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15 39.5 tok/s Runs well
Llama 2 7B ChatMeta · 6.7B 60 ptsGood (B) · 60 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15, workload match +5.0 40.5 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.1 tok/s Runs well
Nemotron Mini 4B InstructNVIDIA · 4.2B 60 ptsGood (B) · 60 of 100 points: Model quality 9.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.3/15, workload match +5.0 41.7 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15, workload match +5.0 69.3 tok/s Runs well
Granite Code 34B InstructIBM · 34B 60 ptsGood (B) · 60 of 100 points: Model quality 15.1/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15 8.1 tok/s Tight fit 70 ptsGood (B) · 70 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15 36.7 tok/s Tight fit
Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active) 60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15, workload match +5.0 67.3 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15, workload match +5.0 181 tok/s Runs well
Zamba2 2.7B InstructZyphra · 2.7B 60 ptsGood (B) · 60 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15, workload match +5.0 40.5 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15, workload match +5.0 109 tok/s Runs well
Baichuan 2 7B ChatBaichuan · 7.5B 60 ptsGood (B) · 60 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 14.3/15, Memory use 8.8/15, workload match +5.0 36.4 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15, workload match +5.0 83.9 tok/s Runs well
Qwen2.5-Math 7B InstructAlibaba · 7.6B 60 ptsGood (B) · 60 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 7.7/15 27.7 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.7/15 82.7 tok/s Runs well
Codestral Mamba 7BMistral AI · 7.3B 60 ptsGood (B) · 60 of 100 points: Model quality 15.4/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 7.3/15 29.0 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15 86.4 tok/s Runs well
Llama 3.2 1B InstructMeta · 1.2B 60 ptsGood (B) · 60 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15, workload match +5.0 40.0 tok/s Runs well 59 ptsGood (B) · 59 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15, workload match +5.0 234 tok/s Runs well
Qwen2.5 1.5B InstructAlibaba · 1.5B 60 ptsGood (B) · 60 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 69.9 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 189 tok/s Runs well
Vicuna 13B v1.5LMSYS · 13B 60 ptsGood (B) · 60 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 11.7/15, workload match +5.0 26.7 tok/s Runs well 69 ptsGood (B) · 69 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.4 tok/s Runs well
LFM2-VL 1.6BLiquid AI · 1.6B 60 ptsGood (B) · 60 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15, workload match +5.0 68.1 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 184 tok/s Runs well
SmolLM2 1.7B InstructHugging Face · 1.7B 60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15, workload match +5.0 62.9 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15, workload match +5.0 170 tok/s Runs well
Code Llama 34B InstructMeta · 34B 60 ptsGood (B) · 60 of 100 points: Model quality 14.4/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15 8.1 tok/s Tight fit 69 ptsGood (B) · 69 of 100 points: Model quality 16.2/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15 36.7 tok/s Tight fit
DeepSeek LLM 7B ChatDeepSeek · 6.9B 60 ptsGood (B) · 60 of 100 points: Model quality 6.8/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 8.3/15, workload match +5.0 39.6 tok/s Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.0 tok/s Runs well
Hunyuan 1.8B InstructTencent · 1.8B 60 ptsGood (B) · 60 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15, workload match +5.0 60.1 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 162 tok/s Runs well
Mathstral 7BMistral AI · 7.3B 59 ptsGood (B) · 59 of 100 points: Model quality 12.9/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15 37.7 tok/s Runs well 70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 40.0 tok/s Runs well
Code Llama 7B InstructMeta · 6.7B 59 ptsGood (B) · 59 of 100 points: Model quality 9.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 40.5 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 43.1 tok/s Runs well
Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active) 59 ptsGood (B) · 59 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15, workload match +5.0 67.3 tok/s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15, workload match +5.0 181 tok/s Runs well
LLaVA 1.5 7BLLaVA · 7.1B 59 ptsGood (B) · 59 of 100 points: Model quality 6.0/45, Memory fit 25.0/25, Speed 14.8/15, Memory use 8.5/15, workload match +5.0 38.7 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.1 tok/s Runs well
Granite Code 8B Instruct (128K)IBM · 8.1B 58 ptsGood (B) · 58 of 100 points: Model quality 12.1/45, Memory fit 25.0/25, Speed 13.8/15, Memory use 8.0/15 34.0 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15 78.2 tok/s Runs well
InternLM2 Math Plus 7BShanghai AI Lab · 7.7B 58 ptsGood (B) · 58 of 100 points: Model quality 12.1/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 7.7/15 35.3 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15 81.4 tok/s Runs well
Gemma 3 1BGoogle · 1.0B 58 ptsGood (B) · 58 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15, workload match +5.0 49.6 tok/s Runs well 57 ptsUsable (C) · 57 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15, workload match +5.0 290 tok/s Runs well
Vicuna 7B v1.5LMSYS · 6.7B 58 ptsGood (B) · 58 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15, workload match +5.0 40.5 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 43.1 tok/s Runs well
InternLM2.5 1.8B ChatShanghai AI Lab · 1.9B 58 ptsGood (B) · 58 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15, workload match +5.0 56.9 tok/s Runs well 59 ptsGood (B) · 59 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15, workload match +5.0 154 tok/s Runs well
Yi 6B Chat01.AI · 6.1B 58 ptsGood (B) · 58 of 100 points: Model quality 7.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.0/15, workload match +5.0 45.1 tok/s Runs well 67 ptsGood (B) · 67 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15, workload match +5.0 47.9 tok/s Runs well
StableLM Zephyr 3BStability AI · 2.8B 58 ptsGood (B) · 58 of 100 points: Model quality 7.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.4/15, workload match +5.0 52.4 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15, workload match +5.0 104 tok/s Runs well
StarCoder 15BBigCode · 16B 57 ptsUsable (C) · 57 of 100 points: Model quality 11.1/45, Memory fit 25.0/25, Speed 8.7/15, Memory use 13.1/15 13.4 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 39.8 tok/s Runs well
Phi-2 2.7BMicrosoft · 2.8B 57 ptsUsable (C) · 57 of 100 points: Model quality 7.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 52.8 tok/s Runs well 59 ptsGood (B) · 59 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.7/15, workload match +5.0 104 tok/s Runs well
OLMo 7B InstructAi2 · 6.9B 57 ptsUsable (C) · 57 of 100 points: Model quality 5.3/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 7.3/15, workload match +5.0 39.7 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 42.1 tok/s Runs well
Granite Code 3B Instruct (128K)IBM · 3.5B 57 ptsUsable (C) · 57 of 100 points: Model quality 8.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15 42.2 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15 83.4 tok/s Runs well
LFM2 700MLiquid AI · 0.7B 57 ptsUsable (C) · 57 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.2/15, workload match +5.0 67.0 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15, workload match +5.0 392 tok/s Runs well
Falcon 3 1B InstructTII · 1.7B 57 ptsUsable (C) · 57 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.0/15, workload match +5.0 64.4 tok/s Runs well 57 ptsUsable (C) · 57 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15, workload match +5.0 174 tok/s Runs well
WizardMath 7B v1.1WizardLM · 7.2B 56 ptsUsable (C) · 56 of 100 points: Model quality 9.8/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 7.5/15 37.7 tok/s Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 40.1 tok/s Runs well
Stable Code Instruct 3BStability AI · 2.8B 56 ptsUsable (C) · 56 of 100 points: Model quality 8.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15 52.4 tok/s Runs well 58 ptsGood (B) · 58 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.7/15 104 tok/s Runs well
Qwen2 1.5B InstructAlibaba · 1.5B 56 ptsUsable (C) · 56 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 69.9 tok/s Runs well 57 ptsUsable (C) · 57 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 189 tok/s Runs well
InternLM 7BShanghai AI Lab · 7.3B 56 ptsUsable (C) · 56 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 14.5/15, Memory use 7.5/15, workload match +5.0 37.3 tok/s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15, workload match +5.0 86.1 tok/s Runs well
DeepScaleR 1.5B PreviewAgentica · 1.8B 56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 60.5 tok/s Runs well 57 ptsUsable (C) · 57 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 163 tok/s Runs well
Qwen3 0.6BAlibaba · 0.8B 56 ptsUsable (C) · 56 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15, workload match +5.0 66.1 tok/s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15, workload match +5.0 387 tok/s Runs well
Qwen2.5 Coder 1.5B InstructAlibaba · 1.5B 56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15 69.9 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15 189 tok/s Runs well
SmolLM 1.7B InstructHugging Face · 1.7B 56 ptsUsable (C) · 56 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 62.9 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15, workload match +5.0 170 tok/s Runs well
OLMo 2 1B InstructAi2 · 1.5B 56 ptsUsable (C) · 56 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15, workload match +5.0 72.7 tok/s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15, workload match +5.0 196 tok/s Runs well
Gemma 2B ITGoogle · 2.5B 55 ptsUsable (C) · 55 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15, workload match +5.0 42.9 tok/s Runs well 57 ptsUsable (C) · 57 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15, workload match +5.0 116 tok/s Runs well
Falcon 40B InstructTII · 42B 55 ptsUsable (C) · 55 of 100 points: Model quality 5.0/45, Memory fit 24.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.3 tok/s Tight fit 65 ptsGood (B) · 65 of 100 points: Model quality 5.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 48.6 tok/s Runs well
StarCoder2 7BBigCode · 7.2B 55 ptsUsable (C) · 55 of 100 points: Model quality 9.1/45, Memory fit 25.0/25, Speed 14.6/15, Memory use 6.9/15 38.1 tok/s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 40.5 tok/s Runs well
Falcon-H1 0.5B InstructTII · 0.5B 55 ptsUsable (C) · 55 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.8/15, workload match +5.0 95.4 tok/s Runs well 54 ptsUsable (C) · 54 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15, workload match +5.0 558 tok/s Runs well
Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50B 54 ptsUsable (C) · 54 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 5.8/15, Memory use 15.0/15, workload match +5.0 5.9 tok/s Heavy offload 68 ptsGood (B) · 68 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 13.2/15, Memory use 15.0/15, workload match +5.0 31.2 tok/s Runs with offload
StableLM 2 1.6B ChatStability AI · 1.6B 54 ptsUsable (C) · 54 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15, workload match +5.0 65.6 tok/s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 177 tok/s Runs well
StableLM 2 Zephyr 1.6BStability AI · 1.6B 54 ptsUsable (C) · 54 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.2/15, workload match +5.0 65.6 tok/s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15, workload match +5.0 177 tok/s Runs well
DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8B 54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 60.5 tok/s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 163 tok/s Runs well
LFM2.5 350MLiquid AI · 0.4B 54 ptsUsable (C) · 54 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15, workload match +5.0 142 tok/s Runs well 53 ptsUsable (C) · 53 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15, workload match +5.0 829 tok/s Runs well
Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active) 54 ptsUsable (C) · 54 of 100 points: Model quality 16.4/45, Memory fit 10.0/25, Speed 8.0/15, Memory use 15.0/15, workload match +5.0 11.4 tok/s Runs with offload 75 ptsGreat (A) · 75 of 100 points: Model quality 16.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 78.8 tok/s Tight fit
Jamba 1.5 MiniAI21 Labs · 52B (12.0B active) 54 ptsUsable (C) · 54 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 8.3/15, Memory use 15.0/15, workload match +5.0 12.3 tok/s Runs with offload 74 ptsGreat (A) · 74 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 84.7 tok/s Tight fit
LFM2-VL 450MLiquid AI · 0.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15, workload match +5.0 110 tok/s Runs well 53 ptsUsable (C) · 53 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15, workload match +5.0 645 tok/s Runs well
Mixtral 8x7B InstructMistral AI · 47B (12.9B active) 53 ptsUsable (C) · 53 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 8.0/15, Memory use 15.0/15, workload match +5.0 11.4 tok/s Runs with offload 74 ptsGreat (A) · 74 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 78.8 tok/s Tight fit
LFM2 350MLiquid AI · 0.4B 53 ptsUsable (C) · 53 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15, workload match +5.0 142 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15, workload match +5.0 829 tok/s Runs well
Granite 4.0 H 350MIBM · 0.3B 53 ptsUsable (C) · 53 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15, workload match +5.0 146 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15, workload match +5.0 854 tok/s Runs well
StarCoder2 3BBigCode · 3.0B 53 ptsUsable (C) · 53 of 100 points: Model quality 8.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15 48.4 tok/s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15 95.8 tok/s Runs well
SmolVLM 500M InstructHugging Face · 0.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.0/15, workload match +5.0 97.3 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15, workload match +5.0 569 tok/s Runs well
Qwen2.5-Math 1.5B InstructAlibaba · 1.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15 69.9 tok/s Runs well 53 ptsUsable (C) · 53 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15 189 tok/s Runs well
Qwen2.5 0.5B InstructAlibaba · 0.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15, workload match +5.0 101 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15, workload match +5.0 592 tok/s Runs well
Hunyuan 0.5B InstructTencent · 0.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15, workload match +5.0 91.9 tok/s Runs well 52 ptsUsable (C) · 52 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15, workload match +5.0 538 tok/s Runs well
Yi Coder 1.5B Chat01.AI · 1.5B 53 ptsUsable (C) · 53 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 72.7 tok/s Runs well 53 ptsUsable (C) · 53 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15 196 tok/s Runs well
TinyLlama 1.1B ChatTinyLlama · 1.1B 52 ptsUsable (C) · 52 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15, workload match +5.0 45.1 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15, workload match +5.0 264 tok/s Runs well
LFM2.5 230MLiquid AI · 0.2B 52 ptsUsable (C) · 52 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15, workload match +5.0 216 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15, workload match +5.0 1,262 tok/s Runs well
Falcon 7B InstructTII · 7.2B 52 ptsUsable (C) · 52 of 100 points: Model quality 1.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.6/15, workload match +5.0 48.1 tok/s Runs well 62 ptsGood (B) · 62 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 40.2 tok/s Runs well
SmolLM2 360M InstructHugging Face · 0.4B 52 ptsUsable (C) · 52 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.6/15, workload match +5.0 138 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15, workload match +5.0 806 tok/s Runs well
CodeGemma 2BGoogle · 2.5B 51 ptsUsable (C) · 51 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15 42.9 tok/s Runs well 53 ptsUsable (C) · 53 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15 116 tok/s Runs well
Qwen2 0.5B InstructAlibaba · 0.5B 51 ptsUsable (C) · 51 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15, workload match +5.0 101 tok/s Runs well 50 ptsUsable (C) · 50 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15, workload match +5.0 592 tok/s Runs well
DeepSeek Coder 1.3B InstructDeepSeek · 1.4B 51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.8/15 79.7 tok/s Runs well 51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15 215 tok/s Runs well
ERNIE 4.5 0.3BBaidu · 0.4B 51 ptsUsable (C) · 51 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15, workload match +5.0 138 tok/s Runs well 50 ptsUsable (C) · 50 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.6/15, workload match +5.0 806 tok/s Runs well
SmolVLM 256M InstructHugging Face · 0.3B 50 ptsUsable (C) · 50 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15, workload match +5.0 191 tok/s Runs well 50 ptsUsable (C) · 50 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15, workload match +5.0 1,117 tok/s Runs well
Gemma 3 270MGoogle · 0.3B 50 ptsUsable (C) · 50 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.1/15, workload match +5.0 184 tok/s Runs well 49 ptsUsable (C) · 49 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15, workload match +5.0 1,075 tok/s Runs well
SmolLM 360M InstructHugging Face · 0.4B 50 ptsUsable (C) · 50 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.4/15, workload match +5.0 138 tok/s Runs well 49 ptsUsable (C) · 49 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15, workload match +5.0 806 tok/s Runs well
SmolLM2 135M InstructHugging Face · 0.1B 49 ptsUsable (C) · 49 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15, workload match +5.0 382 tok/s Runs well 48 ptsUsable (C) · 48 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.2/15, workload match +5.0 2,233 tok/s Runs well
Falcon-H1 Tiny 90M InstructTII · 0.1B 49 ptsUsable (C) · 49 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15, workload match +5.0 551 tok/s Runs well 48 ptsUsable (C) · 48 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.0/15, workload match +5.0 3,226 tok/s Runs well
SmolLM 135M InstructHugging Face · 0.1B 48 ptsUsable (C) · 48 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15, workload match +5.0 382 tok/s Runs well 47 ptsUsable (C) · 47 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.0/15, workload match +5.0 2,233 tok/s Runs well
Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active) 47 ptsUsable (C) · 47 of 100 points: Model quality 15.8/45, Memory fit 4.0/25, Speed 7.7/15, Memory use 15.0/15, workload match +5.0 10.5 tok/s Heavy offload 60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15, workload match +5.0 41.3 tok/s Runs with offload
Qwen2.5 Coder 0.5B InstructAlibaba · 0.5B 47 ptsUsable (C) · 47 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15 101 tok/s Runs well 46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15 592 tok/s Runs well
gpt-oss 120BOpenAI · 117B (5.1B active) 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiMo V2.6 Pro (1T-A42B)Xiaomi · 1,024B (42.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3.8 Max (2.4T-A95B)Alibaba · 2,446B (95.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K3 (2.8T)Moonshot AI · 2,780B (104.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V4 Pro (1.6T-A49B)DeepSeek · 1,651B (49.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Hunyuan Hy4 Preview (780B)Tencent · 780B (55.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2.6 (1T)Moonshot AI · 1,027B (32.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-5.3 Flash (320B-A18B)Zhipu AI · 321B (18.0B active) 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-5.1 (744B-A40B)Zhipu AI · 754B (40.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V4 Pro (April 2026)DeepSeek · 1,599B (49.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3.5 397B-A17BAlibaba · 403B (17.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax M3 (427B)MiniMax · 427B (25.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-5 (744B-A40B)Zhipu AI · 754B (40.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2.5 (1T)Moonshot AI · 1,027B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Ornith 1.5 397B-A17BDeepReinforce · 403B (17.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V3.2 (671B)DeepSeek · 685B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-4.7 (355B-A32B)Zhipu AI · 358B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Nemotron 3 Ultra 550B-A55BNVIDIA · 561B (55.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek R1 0528 (671B)DeepSeek · 685B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2 Thinking (1T)Moonshot AI · 1,026B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V3.2 ExpDeepSeek · 685B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek R1 (671B)DeepSeek · 671B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3.5 122B-A10BAlibaba · 125B (10.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V3.1 TerminusDeepSeek · 685B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V3.1 (671B)DeepSeek · 685B (37.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2 Instruct 0905 (1T)Moonshot AI · 1,026B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Mistral Large 3 (675B)Mistral AI · 675B (41.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Solar Open 2 250BUpstage · 250B (15.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3-VL 235B-A22B InstructAlibaba · 236B (22.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
LongCat Flash Chat (560B)Meituan · 562B (27.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 235B-A22BAlibaba · 235B (22.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Devstral 2 (123B)Mistral AI · 125B 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 253B 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 65 ptsGood (B) · 65 of 100 points: Model quality 32.5/45, Memory fit 4.0/25, Speed 14.5/15, Memory use 15.0/15 37.2 tok/s Heavy offload
Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active) 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 70 ptsGood (B) · 70 of 100 points: Model quality 32.5/45, Memory fit 4.0/25, Speed 14.3/15, Memory use 15.0/15, workload match +5.0 36.4 tok/s Heavy offload
Baichuan M3 235B-A22BBaichuan · 235B (22.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-4.6 (355B-A32B)Zhipu AI · 357B (32.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 70 ptsGood (B) · 70 of 100 points: Model quality 31.8/45, Memory fit 4.0/25, Speed 14.3/15, Memory use 15.0/15, workload match +5.0 36.4 tok/s Heavy offload
DeepSeek V3 0324 (671B)DeepSeek · 685B (37.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-4.6VZhipu AI · 108B (12.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
MiniMax-M1 80KMiniMax · 456B (45.9B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Command A Reasoning (111B)Cohere · 111B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-4.5 (355B-A32B)Zhipu AI · 358B (32.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 3.3 70B InstructMeta · 71B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 59 ptsGood (B) · 59 of 100 points: Model quality 31.0/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
MiniMax-M1 40KMiniMax · 456B (45.9B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Mistral Medium 3.5 (128B)Mistral AI · 128B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Trinity Large Thinking (400B-A13B)Arcee AI · 399B (13.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Command A (111B)Cohere · 111B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
GLM-4.5VZhipu AI · 108B (12.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Hermes 4 405BNous Research · 406B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Kimi Dev 72BMoonshot AI · 73B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 53 ptsUsable (C) · 53 of 100 points: Model quality 30.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15 3.0 tok/s Heavy offload
Mistral Large 2.1 (2411)Mistral AI · 123B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Solar Open 100BUpstage · 103B (12.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 56 ptsUsable (C) · 56 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 7.7/15, Memory use 15.0/15, workload match +5.0 10.5 tok/s Heavy offload
GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Mistral Large 2 (123B)Mistral AI · 123B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Pixtral Large 124B (2411)Mistral AI · 124B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 54 ptsUsable (C) · 54 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 11.0/15, Memory use 15.0/15 21.7 tok/s Heavy offload
dots.llm1 Instructrednote · 143B (14.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 58 ptsGood (B) · 58 of 100 points: Model quality 23.9/45, Memory fit 4.0/25, Speed 11.0/15, Memory use 15.0/15, workload match +5.0 21.7 tok/s Heavy offload
MiniMax-Text-01MiniMax · 456B (45.9B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Tülu 3 405BAi2 · 406B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V3 (671B)DeepSeek · 671B (37.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Sarvam 105BSarvam AI · 106B (10.0B active) 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 56 ptsUsable (C) · 56 of 100 points: Model quality 23.6/45, Memory fit 4.0/25, Speed 8.5/15, Memory use 15.0/15, workload match +5.0 13.0 tok/s Heavy offload
DeepSeek Coder V2 (236B)DeepSeek · 236B (21.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Hermes 4 70BNous Research · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 56 ptsUsable (C) · 56 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 58 ptsGood (B) · 58 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 6.8/15, Memory use 15.0/15, workload match +5.0 8.2 tok/s Heavy offload
InternVL3 78BShanghai AI Lab · 78B 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 55 ptsUsable (C) · 55 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 3.8/15, Memory use 15.0/15, workload match +5.0 2.6 tok/s Heavy offload
Leanstral 119B-A6BMistral AI · 119B (6.5B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen2.5 72B InstructAlibaba · 73B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 55 ptsUsable (C) · 55 of 100 points: Model quality 27.6/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 3.0 tok/s Heavy offload
Qwen2.5-VL 72B InstructAlibaba · 73B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 55 ptsUsable (C) · 55 of 100 points: Model quality 27.6/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 2.9 tok/s Heavy offload
DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek R1 Distill Llama 70BDeepSeek · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 50 ptsUsable (C) · 50 of 100 points: Model quality 27.2/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15 3.2 tok/s Heavy offload
DeepSeek V2.5 1210DeepSeek · 236B (21.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 3.1 405B InstructMeta · 406B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 4 Maverick (17B x 128E)Meta · 402B (17.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 4 Scout 17B-16EMeta · 109B (17.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Tülu 3 70BAi2 · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 55 ptsUsable (C) · 55 of 100 points: Model quality 27.2/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Command R+ (08-2024) 104BCohere · 104B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
DeepSeek V2.5DeepSeek · 236B (21.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Jamba 1.5 LargeAI21 Labs · 399B (94.0B active) 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Llama 3.1 70B InstructMeta · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.6/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 54 ptsUsable (C) · 54 of 100 points: Model quality 26.5/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Hermes 3 (Llama 3.1 70B)Nous Research · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 53 ptsUsable (C) · 53 of 100 points: Model quality 25.7/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
QVQ 72B PreviewAlibaba · 73B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 53 ptsUsable (C) · 53 of 100 points: Model quality 25.7/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 2.9 tok/s Heavy offload
Apertus v1.5 70BSwiss AI · 72B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 53 ptsUsable (C) · 53 of 100 points: Model quality 24.9/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 3.0 tok/s Heavy offload
Llama 3.1 Nemotron 70B InstructNVIDIA · 71B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 53 ptsUsable (C) · 53 of 100 points: Model quality 24.9/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Llama 3.2 90B Vision InstructMeta · 89B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 48 ptsUsable (C) · 48 of 100 points: Model quality 20.8/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 3.0 tok/s Heavy offload
Command R+ 104B (04-2024)Cohere · 104B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Qwen2 72B InstructAlibaba · 73B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 52 ptsUsable (C) · 52 of 100 points: Model quality 24.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 3.0 tok/s Heavy offload
Qwen2-VL 72B InstructAlibaba · 73B 6 ptsWon't run (F) · 6 of 100 points: Model quality 6.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 52 ptsUsable (C) · 52 of 100 points: Model quality 24.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15, workload match +5.0 2.9 tok/s Heavy offload
DeepSeek V2 ChatDeepSeek · 236B (21.0B active) 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Apertus 70B InstructSwiss AI · 71B 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 50 ptsUsable (C) · 50 of 100 points: Model quality 22.7/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Llama 3 70B InstructMeta · 71B 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 50 ptsUsable (C) · 50 of 100 points: Model quality 21.9/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15, workload match +5.0 3.2 tok/s Heavy offload
Qwen2.5-Math 72B InstructAlibaba · 73B 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.5/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 48 ptsUsable (C) · 48 of 100 points: Model quality 18.3/45, Memory fit 10.0/25, Speed 5.6/15, Memory use 15.0/15 5.6 tok/s Runs with offload
Mixtral 8x22B InstructMistral AI · 141B (39.0B active) 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Command R 35B (v01)Cohere · 35B 5 ptsWon't run (F) · 5 of 100 points: Model quality 5.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 56 ptsUsable (C) · 56 of 100 points: Model quality 17.0/45, Memory fit 10.0/25, Speed 9.6/15, Memory use 15.0/15, workload match +5.0 16.4 tok/s Runs with offload
Qwen1.5 110B ChatAlibaba · 111B 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Aya 23 35BCohere · 35B 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 55 ptsUsable (C) · 55 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 9.6/15, Memory use 15.0/15, workload match +5.0 16.4 tok/s Runs with offload
Grok-1 (314B)xAI · 314B (86.0B active) 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Snowflake Arctic InstructSnowflake · 479B (17.0B active) 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.7/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Code Llama 70B InstructMeta · 69B 4 ptsWon't run (F) · 4 of 100 points: Model quality 4.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 44 ptsUsable (C) · 44 of 100 points: Model quality 13.9/45, Memory fit 10.0/25, Speed 6.1/15, Memory use 15.0/15 6.6 tok/s Runs with offload
DeepSeek LLM 67B ChatDeepSeek · 67B 3 ptsWon't run (F) · 3 of 100 points: Model quality 3.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 48 ptsUsable (C) · 48 of 100 points: Model quality 12.6/45, Memory fit 10.0/25, Speed 6.3/15, Memory use 15.0/15, workload match +5.0 7.0 tok/s Runs with offload
Llama 2 70B ChatMeta · 69B 3 ptsWon't run (F) · 3 of 100 points: Model quality 3.4/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 47 ptsUsable (C) · 47 of 100 points: Model quality 11.3/45, Memory fit 10.0/25, Speed 6.1/15, Memory use 15.0/15, workload match +5.0 6.6 tok/s Runs with offload
Falcon 180B ChatTII · 180B 3 ptsWon't run (F) · 3 of 100 points: Model quality 3.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 3 ptsWon't run (F) · 3 of 100 points: Model quality 3.2/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run

Image models

Model Grade · points (Apple M2 Pro (32 GB)) Time (Apple M2 Pro (32 GB)) Fit (Apple M2 Pro (32 GB)) Grade · points (NVIDIA GeForce RTX 4090) Time (NVIDIA GeForce RTX 4090) Fit (NVIDIA GeForce RTX 4090)
FLUX.2 [klein] 9BBlack Forest Labs · 9.1B 85 ptsExcellent (S) · 85 of 100 points: Model quality 37.0/45, Memory fit 23.0/25, Speed 10.6/15, Memory use 15.0/15 20 s Tight fit 92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 1.6 s Runs well
FLUX.2 [klein] 4BBlack Forest Labs · 3.9B 84 ptsGreat (A) · 84 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 14.2/15, Memory use 11.0/15 11 s Runs well 90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 1.0 s Runs well
Z-Image TurboAlibaba (Tongyi) · 6.2B 84 ptsGreat (A) · 84 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 9.0/15, Memory use 13.5/15 28 s Runs well 89 ptsExcellent (S) · 89 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15 2.9 s Runs well
FLUX.1 [schnell]Black Forest Labs · 11.9B 78 ptsGreat (A) · 78 of 100 points: Model quality 30.9/45, Memory fit 23.0/25, Speed 10.1/15, Memory use 15.0/15 22 s Tight fit 85 ptsExcellent (S) · 85 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 1.8 s Runs well
Stable Diffusion 3.5 Large TurboStability AI · 8.1B 78 ptsGreat (A) · 78 of 100 points: Model quality 27.3/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 15.0/15 18 s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 1.8 s Runs well
FLUX.1 Krea [dev]Black Forest Labs · 11.9B 78 ptsGreat (A) · 78 of 100 points: Model quality 36.2/45, Memory fit 23.0/25, Speed 4.1/15, Memory use 15.0/15 2.2 min Tight fit 90 ptsExcellent (S) · 90 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15 11 s Runs well
Z-ImageAlibaba (Tongyi) · 6.2B 78 ptsGreat (A) · 78 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 3.4/15, Memory use 13.5/15 3.2 min Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 12.1/15 15 s Runs well
Chroma1-HDLodestone Rock · 8.9B 77 ptsGreat (A) · 77 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 3.2/15, Memory use 15.0/15 3.7 min Runs well 85 ptsExcellent (S) · 85 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 15.0/15 18 s Runs well
FLUX.1 [dev]Black Forest Labs · 11.9B 77 ptsGreat (A) · 77 of 100 points: Model quality 35.3/45, Memory fit 23.0/25, Speed 4.1/15, Memory use 15.0/15 2.2 min Tight fit 89 ptsExcellent (S) · 89 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15 11 s Runs well
FLUX.1 Kontext [dev]Black Forest Labs · 11.9B 77 ptsGreat (A) · 77 of 100 points: Model quality 36.2/45, Memory fit 23.0/25, Speed 3.0/15, Memory use 15.0/15 4.1 min Tight fit 86 ptsExcellent (S) · 86 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15 20 s Runs well
FLUX.1 Fill [dev]Black Forest Labs · 11.9B 75 ptsGreat (A) · 75 of 100 points: Model quality 33.5/45, Memory fit 23.0/25, Speed 4.0/15, Memory use 15.0/15 2.3 min Tight fit 87 ptsExcellent (S) · 87 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 15.0/15 11 s Runs well
CogView4 6BZhipu AI · 6.4B 74 ptsGreat (A) · 74 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 3.4/15, Memory use 15.0/15 3.3 min Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 15.0/15 16 s Runs well
SDXL-Lightning (4-step)ByteDance · 2.6B 73 ptsGreat (A) · 73 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.6/15 8.7 s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 0.7 s Runs well
Stable Diffusion 3.5 LargeStability AI · 8.1B 73 ptsGreat (A) · 73 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 4.3/15, Memory use 15.0/15 2.0 min Runs well 84 ptsGreat (A) · 84 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 9.9 s Runs well
OmniGen2BAAI (VectorSpaceLab) · 4.0B 73 ptsGreat (A) · 73 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 3.4/15, Memory use 15.0/15 3.3 min Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 9.9/15 14 s Runs well
Qwen-Image-Edit 2511Alibaba · 20.4B 72 ptsGreat (A) · 72 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 1.3/15, Memory use 15.0/15 20.8 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 4.7/15, Memory use 15.0/15 1.7 min Runs well
PixArt-Σ XL 1024PixArt · 0.6B 72 ptsGreat (A) · 72 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 11.0/15, Memory use 13.8/15 19 s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 1.5 s Runs well
HiDream-I1 FullHiDream.ai · 17.1B 72 ptsGreat (A) · 72 of 100 points: Model quality 37.0/45, Memory fit 18.0/25, Speed 2.1/15, Memory use 15.0/15 8.8 min Tight fit 79 ptsGreat (A) · 79 of 100 points: Model quality 37.0/45, Memory fit 20.0/25, Speed 7.3/15, Memory use 15.0/15 43 s Runs well
Qwen-Image 2512Alibaba · 20.4B 71 ptsGood (B) · 71 of 100 points: Model quality 37.7/45, Memory fit 18.0/25, Speed 1.3/15, Memory use 15.0/15 23.4 min Tight fit 77 ptsGreat (A) · 77 of 100 points: Model quality 37.7/45, Memory fit 20.0/25, Speed 4.5/15, Memory use 15.0/15 1.9 min Runs well
Lumina-Image 2.0Shanghai AI Lab · 2.6B 71 ptsGood (B) · 71 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 5.1/15, Memory use 13.7/15 87 s Runs well 80 ptsGreat (A) · 80 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15 7.0 s Runs well
HiDream-I1 DevHiDream.ai · 17.1B 71 ptsGood (B) · 71 of 100 points: Model quality 35.3/45, Memory fit 18.0/25, Speed 3.4/15, Memory use 15.0/15 3.3 min Tight fit 82 ptsGreat (A) · 82 of 100 points: Model quality 35.3/45, Memory fit 20.0/25, Speed 11.8/15, Memory use 15.0/15 16 s Runs well
Stable Diffusion 3 MediumStability AI · 2.0B 71 ptsGood (B) · 71 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 7.7/15, Memory use 15.0/15 38 s Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 3.1 s Runs well
HiDream-I1 FastHiDream.ai · 17.1B 70 ptsGood (B) · 70 of 100 points: Model quality 33.5/45, Memory fit 18.0/25, Speed 4.4/15, Memory use 15.0/15 1.9 min Tight fit 83 ptsGreat (A) · 83 of 100 points: Model quality 33.5/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15 9.5 s Runs well
KolorsKuaishou · 2.6B 70 ptsGood (B) · 70 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 7.1/15, Memory use 11.8/15 45 s Runs well 82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 4.0 s Runs well
FLUX.2 [dev]Black Forest Labs · 32.2B 69 ptsGood (B) · 69 of 100 points: Model quality 41.0/45, Memory fit 12.0/25, Speed 1.8/15, Memory use 15.0/15 11.1 min Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 38.5/45, Memory fit 18.0/25, Speed 7.0/15, Memory use 15.0/15 45 s Tight fit
Stable CascadeStability AI · 5.2B 69 ptsGood (B) · 69 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 6.0/15, Memory use 15.0/15 62 s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15 5.0 s Runs well
DreamShaper XL v2 TurboLykon · 2.6B 69 ptsGood (B) · 69 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 6.0/15 14 s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 1.3 s Runs well
Juggernaut XL v9RunDiffusion · 2.6B 68 ptsGood (B) · 68 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 9.6/15 56 s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.5 s Runs well
RealVisXL V5.0SG161222 · 2.6B 68 ptsGood (B) · 68 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 9.6/15 56 s Runs well 76 ptsGreat (A) · 76 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.5 s Runs well
Animagine XL 4.0Cagliostro Lab · 2.6B 68 ptsGood (B) · 68 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 9.6/15 52 s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.2 s Runs well
Illustrious XL v0.1OnomaAI · 2.6B 68 ptsGood (B) · 68 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 9.6/15 52 s Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.2 s Runs well
Pony Diffusion V6 XLPurpleSmartAI · 2.6B 67 ptsGood (B) · 67 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 6.9/15, Memory use 9.6/15 47 s Runs well 74 ptsGreat (A) · 74 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 3.8 s Runs well
Stable Diffusion 3.5 MediumStability AI · 2.5B 67 ptsGood (B) · 67 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 5.8/15, Memory use 11.1/15 67 s Runs well 81 ptsGreat (A) · 81 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 6.0 s Runs well
Playground v2.5Playground AI · 2.6B 66 ptsGood (B) · 66 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 4.9/15, Memory use 9.6/15 1.5 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 7.5 s Runs well
Animagine XL 3.1Cagliostro Lab · 2.6B 66 ptsGood (B) · 66 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 6.6/15, Memory use 9.6/15 52 s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.2 s Runs well
Qwen-ImageAlibaba · 20.4B 66 ptsGood (B) · 66 of 100 points: Model quality 38.8/45, Memory fit 12.0/25, Speed 1.3/15, Memory use 14.3/15 21.7 min Runs well 68 ptsGood (B) · 68 of 100 points: Model quality 38.8/45, Memory fit 12.0/25, Speed 4.6/15, Memory use 12.8/15 1.8 min Runs well
SDXL TurboStability AI · 2.6B 66 ptsGood (B) · 66 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15 1.9 s Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15 0.2 s Runs well
Stable Diffusion XL 1.0Stability AI · 2.6B 65 ptsGood (B) · 65 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 6.4/15, Memory use 9.6/15 56 s Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15 4.5 s Runs well
AuraFlow v0.3fal · 6.9B 65 ptsGood (B) · 65 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 3.8/15, Memory use 11.2/15 2.6 min Runs well 73 ptsGreat (A) · 73 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 10.0/15 13 s Runs well
Hunyuan-DiT v1.2Tencent · 1.5B 63 ptsGood (B) · 63 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 5.5/15, Memory use 10.0/15 74 s Runs well 72 ptsGreat (A) · 72 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15 6.0 s Runs well
Realistic Vision V5.1SG161222 · 0.9B 59 ptsGood (B) · 59 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 3.0/15 15 s Runs well 61 ptsGood (B) · 61 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 1.2 s Runs well
DreamShaper 8Lykon · 0.9B 58 ptsGood (B) · 58 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 3.0/15 15 s Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 1.2 s Runs well
LCM DreamShaper v7Tsinghua (LCM) · 0.9B 56 ptsUsable (C) · 56 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15 3.1 s Runs well 56 ptsUsable (C) · 56 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 0.3 s Runs well
SD TurboStability AI · 0.9B 56 ptsUsable (C) · 56 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15 1.0 s Runs well 55 ptsUsable (C) · 55 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15 0.1 s Runs well
Stable Diffusion 1.5Stability AI / Runway · 0.9B 56 ptsUsable (C) · 56 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 3.0/15 15 s Runs well 58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15 1.2 s Runs well
Kandinsky 3Sber AI · 3.0B 55 ptsUsable (C) · 55 of 100 points: Model quality 21.6/45, Memory fit 20.0/25, Speed 4.4/15, Memory use 9.3/15 1.9 min Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 21.6/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 8.3/15 9.5 s Runs well
HunyuanImage 3.0 (80B-A13B)Tencent · 83.0B 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run

Video models

Model Grade · points (Apple M2 Pro (32 GB)) Time (Apple M2 Pro (32 GB)) Fit (Apple M2 Pro (32 GB)) Grade · points (NVIDIA GeForce RTX 4090) Time (NVIDIA GeForce RTX 4090) Fit (NVIDIA GeForce RTX 4090)
LTX-Video 2BLightricks · 1.9B 70 ptsGood (B) · 70 of 100 points: Model quality 22.1/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 11.6/15 4.6 min Runs well 77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 25 s Runs well
Wan 2.1 I2V 14B 480PAlibaba · 14.0B 70 ptsGood (B) · 70 of 100 points: Model quality 31.0/45, Memory fit 23.0/25, Speed 1.7/15, Memory use 15.0/15 3.7 h Tight fit 75 ptsGreat (A) · 75 of 100 points: Model quality 31.0/45, Memory fit 23.0/25, Speed 6.1/15, Memory use 15.0/15 18.0 min Tight fit
CogVideoX 5BZhipu AI · 5.0B 68 ptsGood (B) · 68 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15 33.4 min Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15 2.7 min Runs well
CogVideoX 5B I2VZhipu AI · 5.6B 68 ptsGood (B) · 68 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 4.5/15, Memory use 15.0/15 33.4 min Runs well 78 ptsGreat (A) · 78 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.3/15 2.7 min Runs well
FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9B 68 ptsGood (B) · 68 of 100 points: Model quality 32.6/45, Memory fit 18.0/25, Speed 2.9/15, Memory use 15.0/15 77.9 min Tight fit 77 ptsGreat (A) · 77 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 10.4/15, Memory use 15.0/15 6.3 min Runs well
Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3B 68 ptsGood (B) · 68 of 100 points: Model quality 31.8/45, Memory fit 20.0/25, Speed 1.6/15, Memory use 15.0/15 4.3 h Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 31.8/45, Memory fit 23.0/25, Speed 5.8/15, Memory use 15.0/15 20.0 min Tight fit
Wan 2.1 VACE 1.3BAlibaba · 2.2B 67 ptsGood (B) · 67 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 3.7/15, Memory use 14.7/15 48.2 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 13.2/15 3.9 min Runs well
CogVideoX 2BZhipu AI · 1.7B 67 ptsGood (B) · 67 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 15.0/15 12.4 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 60 s Runs well
Wan 2.1 T2V 1.3BAlibaba · 1.3B 66 ptsGood (B) · 66 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 3.9/15, Memory use 13.8/15 44.5 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 13.7/15, Memory use 12.4/15 3.6 min Runs well
SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4B 66 ptsGood (B) · 66 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 3.5/15, Memory use 15.0/15 55.6 min Runs well 75 ptsGreat (A) · 75 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 15.0/15 4.5 min Runs well
LTX-2.3Lightricks · 18.9B 65 ptsGood (B) · 65 of 100 points: Model quality 38.3/45, Memory fit 10.0/25, Speed 2.3/15, Memory use 15.0/15 2.1 h Tight fit 74 ptsGreat (A) · 74 of 100 points: Model quality 37.9/45, Memory fit 12.0/25, Speed 9.3/15, Memory use 15.0/15 7.8 min Runs well
LTX-2 (19B, video + audio)Lightricks · 18.9B 63 ptsGood (B) · 63 of 100 points: Model quality 36.5/45, Memory fit 10.0/25, Speed 2.3/15, Memory use 15.0/15 2.1 h Tight fit 72 ptsGreat (A) · 72 of 100 points: Model quality 36.2/45, Memory fit 12.0/25, Speed 9.3/15, Memory use 15.0/15 7.8 min Runs well
LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0B 63 ptsGood (B) · 63 of 100 points: Model quality 30.0/45, Memory fit 12.0/25, Speed 6.8/15, Memory use 15.0/15 14.5 min Runs well 71 ptsGood (B) · 71 of 100 points: Model quality 30.0/45, Memory fit 12.0/25, Speed 15.0/15, Memory use 15.0/15 70 s Runs well
SkyReels V2 T2V 14B 540PSkywork · 14.0B 61 ptsGood (B) · 61 of 100 points: Model quality 32.6/45, Memory fit 12.0/25, Speed 1.4/15, Memory use 15.0/15 5.6 h Runs well 65 ptsGood (B) · 65 of 100 points: Model quality 33.3/45, Memory fit 12.0/25, Speed 4.7/15, Memory use 15.0/15 30.3 min Runs well
AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3B 58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 12.8/15, Memory use 5.1/15 4.1 min Runs well 60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15 20 s Runs well
Open-Sora 2.0 (11B)HPC-AI Tech · 11.0B 57 ptsUsable (C) · 57 of 100 points: Model quality 31.5/45, Memory fit 10.0/25, Speed 0.9/15, Memory use 15.0/15 13.4 h Tight fit 61 ptsGood (B) · 61 of 100 points: Model quality 31.5/45, Memory fit 12.0/25, Speed 3.2/15, Memory use 15.0/15 65.0 min Runs well
Mochi 1 Preview (10B)Genmo · 10.0B 56 ptsUsable (C) · 56 of 100 points: Model quality 27.9/45, Memory fit 12.0/25, Speed 1.5/15, Memory use 15.0/15 4.9 h Runs well 66 ptsGood (B) · 66 of 100 points: Model quality 27.3/45, Memory fit 18.0/25, Speed 6.2/15, Memory use 15.0/15 17.3 min Tight fit
Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0B 53 ptsUsable (C) · 53 of 100 points: Model quality 25.6/45, Memory fit 10.0/25, Speed 3.3/15, Memory use 15.0/15 60.3 min Tight fit 71 ptsGood (B) · 71 of 100 points: Model quality 25.6/45, Memory fit 18.0/25, Speed 13.1/15, Memory use 15.0/15 3.9 min Tight fit
HunyuanVideo 1.5 (8.3B)Tencent · 8.3B 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 11 ptsWon't run (F) · 11 of 100 points: Model quality 11.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Wan 2.2 I2V A14BAlibaba · 14.0B 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 67 ptsGood (B) · 67 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 4.7/15, Memory use 15.0/15 31.2 min Tight fit
Wan 2.2 T2V A14BAlibaba · 14.0B 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 67 ptsGood (B) · 67 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 4.7/15, Memory use 15.0/15 31.2 min Tight fit
SkyReels V2 T2V 14B 720PSkywork · 14.0B 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Step-Video T2V (30B)StepFun · 30.0B 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 10 ptsWon't run (F) · 10 of 100 points: Model quality 10.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Wan 2.1 I2V 14B 720PAlibaba · 14.0B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 63 ptsGood (B) · 63 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 4.2/15, Memory use 15.0/15 39.0 min Tight fit
Wan 2.1 T2V 14BAlibaba · 14.0B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 63 ptsGood (B) · 63 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 4.2/15, Memory use 15.0/15 39.0 min Tight fit
Wan 2.1 VACE 14BAlibaba · 17.3B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 61 ptsGood (B) · 61 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 3.4/15, Memory use 15.0/15 57.2 min Tight fit
Wan 2.2 Animate 14BAlibaba · 17.3B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 61 ptsGood (B) · 61 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 3.7/15, Memory use 15.0/15 49.4 min Tight fit
Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.3/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
HunyuanVideo 13BTencent · 13.0B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
HunyuanVideo I2V 13BTencent · 13.0B 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 9 ptsWon't run (F) · 9 of 100 points: Model quality 9.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Wan 2.2 TI2V 5BAlibaba · 5.0B 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.8/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 64 ptsGood (B) · 64 of 100 points: Model quality 30.9/45, Memory fit 10.0/25, Speed 8.2/15, Memory use 15.0/15 10.1 min Tight fit
Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0B 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 8 ptsWon't run (F) · 8 of 100 points: Model quality 8.1/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
CogVideoX 1.5 5BZhipu AI · 5.6B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.9/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run
Allegro (2.8B)Rhymes AI · 2.8B 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run 7 ptsWon't run (F) · 7 of 100 points: Model quality 7.0/45, Memory fit 0.0/25, Speed 0.0/15, Memory use 0.0/15 — Won't run

Swap sides All models on the Apple M2 Pro (32 GB) All models on the NVIDIA GeForce RTX 4090

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.