Check my GPU

What your NVIDIA GeForce RTX 4090 can run

We check your graphics card or Mac against every model in the catalog. Your browser reports the GPU model but not its memory, so confirm the exact version below.

VRAM
24.0 GB
Usable for models
24.0 GB
Memory bandwidth
1,008 GB/s
FP16 compute
82.6 TFLOPS
439 / 536 LLMs run Best: Qwen3.8 27B (S) 46 / 47 Image models run Best: FLUX.2 [klein] 9B (S) 25 / 34 Video models run Best: CogVideoX 5B I2V (A)

Open in Model Finder Best LLMs by task Compare with another GPU

LLMs on your NVIDIA GeForce RTX 4090

Grade · points Model Quant Memory Speed Fit
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3.8 27BAlibaba · 28BQ4_K_M19.3 GB44.5 tok/sRuns well
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Gemma 4 26B-A4BGoogle · 26B (3.8B active)Q6_K23.4 GB113 tok/sTight fit
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3.6 27BAlibaba · 28BQ4_K_M19.3 GB44.5 tok/sRuns well
94 ptsExcellent (S) · 94 of 100 points: Model quality 39.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3.5 27BAlibaba · 28BQ4_K_M19.3 GB44.5 tok/sRuns well
93 ptsExcellent (S) · 93 of 100 points: Model quality 40.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M23.9 GB206 tok/sTight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M23.9 GB206 tok/sTight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 38.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15TMax 27BAi2 · 27BQ4_K_M19.0 GB45.2 tok/sRuns well
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.9/45, Memory fit 24.0/25, Speed 14.9/15, Memory use 15.0/15Gemma 4 31BGoogle · 31BQ4_K_M22.5 GB39.6 tok/sTight fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Fara 1.5 27BMicrosoft · 27BQ4_K_M19.0 GB45.2 tok/sRuns well
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M23.9 GB206 tok/sTight fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)Q4_K_M23.9 GB206 tok/sTight fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 38.0/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M23.9 GB206 tok/sTight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.6/15Gemma 4 12BGoogle · 12BQ8_015.1 GB52.7 tok/sRuns well
91 ptsExcellent (S) · 91 of 100 points: Model quality 36.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15UI-Mate 27BTencent · 27BQ4_K_M19.0 GB45.2 tok/sRuns well
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)Q4_K_M21.3 GB206 tok/sTight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Agents-A1 35B-A3BInternScience · 35B (3.0B active)Q4_K_M23.4 GB206 tok/sTight fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 37.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)Q4_K_M23.1 GB206 tok/sTight fit
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)Q4_K_M23.5 GB206 tok/sTight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)Q5_K_M23.7 GB170 tok/sTight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)Q6_K23.4 GB107 tok/sTight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 35.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15EXAONE 4.5 33BLG AI Research · 34BQ4_K_M23.5 GB36.0 tok/sTight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 34.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M21.1 GB177 tok/sTight fit
88 ptsExcellent (S) · 88 of 100 points: Model quality 33.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Devstral Small 2 (24B)Mistral AI · 24BQ5_K_M20.2 GB42.6 tok/sRuns well
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Apriel 1.5 15B ThinkerServiceNow · 15BQ8_019.2 GB42.4 tok/sRuns well
87 ptsExcellent (S) · 87 of 100 points: Model quality 32.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-4 Reasoning Plus (14B)Microsoft · 15BQ8_019.0 GB43.0 tok/sRuns well
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)Q4_K_M21.2 GB187 tok/sTight fit
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M21.2 GB187 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 33.3/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15QwQ 32BAlibaba · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M21.1 GB177 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)Q4_K_M21.2 GB187 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-4 Reasoning (14B)Microsoft · 15BQ8_019.0 GB43.0 tok/sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-4 Reasoning Vision 15BMicrosoft · 15BQ8_019.5 GB41.7 tok/sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Granite 4.2 30BIBM · 29BQ4_K_M21.8 GB42.3 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)Q4_K_M21.6 GB187 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 34.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15Ornith 1.5 9BDeepReinforce · 9.7BQ8_012.3 GB65.3 tok/sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Magistral Small 1.2 (24B)Mistral AI · 24BQ5_K_M20.2 GB42.6 tok/sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15Olmo 3.1 32B ThinkAi2 · 32BQ4_K_M22.2 GB38.4 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 31.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)Q6_K20.2 GB143 tok/sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15OpenReasoning Nemotron 32BNVIDIA · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Skywork OR1 32BSkywork · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 32.5/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Qwen3 32BAlibaba · 33BQ4_K_M24.0 GB37.7 tok/sTight fit
86 ptsExcellent (S) · 86 of 100 points: Model quality 34.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15Qwen3.5 9BAlibaba · 9.7BQ8_012.3 GB65.3 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Gemma 3 27B ITGoogle · 27BQ4_K_M19.3 GB45.2 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M21.2 GB187 tok/sTight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)Q4_K_M21.6 GB187 tok/sTight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3 14BAlibaba · 15BQ8_018.8 GB42.6 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 33.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15Ornith 1.0 9BDeepReinforce · 9.7BQ8_012.3 GB65.3 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Devstral Small 1.1 (24B)Mistral AI · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Magistral Small 2507Mistral AI · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15EXAONE Deep 32BLG AI Research · 32BQ4_K_M23.5 GB38.7 tok/sTight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15GLM-4 32B 0414Zhipu AI · 33BQ4_K_M22.2 GB38.0 tok/sTight fit
85 ptsExcellent (S) · 85 of 100 points: Model quality 31.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15GLM-Z1 32B (0414)Zhipu AI · 33BQ4_K_M22.2 GB38.0 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 29.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15MedGemma 27B Text ITGoogle · 27BQ4_K_M19.1 GB45.8 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15gpt-oss 20BOpenAI · 21B (3.6B active)MXFP413.9 GB184 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Granite 4.1 30BIBM · 29BQ4_K_M21.6 GB42.9 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)Q4_K_M21.1 GB206 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15AceReason Nemotron 14BNVIDIA · 15BQ8_019.1 GB42.6 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Apriel Nemotron 15B ThinkerServiceNow · 15BQ8_019.3 GB42.1 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Hermes 4 14BNous Research · 15BQ8_018.8 GB42.6 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Ministral 3 14B ReasoningMistral AI · 14BQ8_017.9 GB45.2 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OpenReasoning Nemotron 14BNVIDIA · 15BQ8_019.1 GB42.6 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen2.5 Coder 14B InstructAlibaba · 15BQ8_019.1 GB42.6 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Magistral Small 2506Mistral AI · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral Small 3.2 24BMistral AI · 24BQ5_K_M20.2 GB42.6 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15EXAONE 4.0 32BLG AI Research · 32BQ4_K_M22.1 GB38.7 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 29.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3-VL 32B InstructAlibaba · 33BQ3_K_M20.3 GB48.0 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15Olmo 3.1 32B InstructAi2 · 32BQ4_K_M22.2 GB38.4 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 33.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15TMax 9BAi2 · 9.0BQ8_011.6 GB70.4 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Reka Flash 3.1 (21B)Reka AI · 21BQ6_K20.1 GB41.1 tok/sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 30.8/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15DeepSeek R1 Distill Qwen 32BDeepSeek · 33BQ4_K_M24.0 GB37.7 tok/sTight fit
84 ptsGreat (A) · 84 of 100 points: Model quality 30.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Seed-OSS 36B InstructByteDance · 36BQ3_K_M21.7 GB44.2 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Sarvam 30BSarvam AI · 32B (2.4B active)Q4_K_M21.6 GB258 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Hermes 4.3 36BNous Research · 36BQ3_K_M21.7 GB44.2 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Devstral Small 2505Mistral AI · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral Small 3.1 24BMistral AI · 24BQ5_K_M20.2 GB42.6 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepCoder 14B PreviewAgentica · 15BQ8_019.1 GB42.6 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15InternVL3 14BShanghai AI Lab · 15BQ8_019.4 GB41.7 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Ministral 3 14BMistral AI · 14BQ8_017.9 GB45.2 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-4 (14B)Microsoft · 15BQ8_019.1 GB42.9 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 28.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)Q6_K20.3 GB143 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Baichuan M2 32BBaichuan · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15OpenHands LM 32BAll Hands AI · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.9/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Qwen2.5 32B InstructAlibaba · 33BQ4_K_M24.0 GB37.7 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 29.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)Q6_K23.4 GB143 tok/sTight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15UI-Mate 9BTencent · 9.4BQ8_012.0 GB66.9 tok/sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 31.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15UI-Venus 2 9BAnt Group (inclusionAI) · 9.4BQ8_012.0 GB66.9 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral Small 3 24B (2501)Mistral AI · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek R1 Distill Qwen 14BDeepSeek · 15BQ8_019.1 GB42.6 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15JanusCoder 14BShanghai AI Lab · 15BQ8_018.8 GB42.6 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen2.5 14B InstructAlibaba · 15BQ8_019.0 GB42.9 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 28.7/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15InternVL3.5 38BShanghai AI Lab · 38BQ3_K_M22.8 GB41.7 tok/sTight fit
82 ptsGreat (A) · 82 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15Granite 4.2 8BIBM · 8.8BQ8_012.5 GB71.7 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 28.6/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Qwen2.5 Coder 32B InstructAlibaba · 33BQ4_K_M24.0 GB37.7 tok/sTight fit
82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Codestral 22BMistral AI · 22BQ5_K_M19.5 GB45.9 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Dolphin Mistral 24B Venice EditionCognitive Computations · 24BQ5_K_M20.2 GB42.6 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Voxtral Small 24BMistral AI · 24BQ5_K_M20.4 GB42.1 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)Q8_019.4 GB105 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)F1617.8 GB112 tok/sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen2.5 14B Instruct 1MAlibaba · 15BQ8_019.1 GB42.6 tok/sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.8/15Gemma 3 12B ITGoogle · 12BQ8_015.4 GB51.6 tok/sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 28.2/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15QwQ 32B PreviewAlibaba · 33BQ4_K_M23.9 GB37.8 tok/sTight fit
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Gemma 2 27B ITGoogle · 27BQ4_K_M20.1 GB45.5 tok/sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)Q3_K_M19.9 GB242 tok/sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24BQ5_K_M19.9 GB43.4 tok/sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Solar Pro Preview 22BUpstage · 22BQ5_K_M18.9 GB46.2 tok/sRuns well
80 ptsGreat (A) · 80 of 100 points: Model quality 27.4/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15Falcon-H1 34B InstructTII · 34BQ4_K_M23.5 GB36.8 tok/sTight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 25.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen2.5-VL 32B InstructAlibaba · 33BQ3_K_M20.3 GB47.8 tok/sRuns well
80 ptsGreat (A) · 80 of 100 points: Model quality 30.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15Gemma 4 E4BGoogle · 8.0BQ8_010.4 GB78.7 tok/sRuns well
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)Q4_K_M21.6 GB68.7 tok/sTight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15InternVL3 38BShanghai AI Lab · 38BQ3_K_M22.8 GB41.7 tok/sTight fit
80 ptsGreat (A) · 80 of 100 points: Model quality 26.5/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15Command R (08-2024) 32BCohere · 32BQ4_K_M22.8 GB38.3 tok/sTight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15Qwen3-VL 8B InstructAlibaba · 8.8BQ8_012.3 GB71.8 tok/sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15Gemma 4 E2BGoogle · 5.1BF1612.1 GB56.7 tok/sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15GLM-4.1V 9B ThinkingZhipu AI · 10BQ8_013.0 GB61.2 tok/sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15InternVL3.5 8BShanghai AI Lab · 8.5BQ8_012.0 GB73.8 tok/sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 24.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LFM2 24B-A2BLiquid AI · 24B (2.3B active)Q5_K_M18.9 GB222 tok/sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15OLMo 2 32B InstructAi2 · 32BQ4_K_M22.5 GB38.4 tok/sTight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15Aya Expanse 32BCohere · 32BQ4_K_M22.8 GB38.3 tok/sTight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 25.7/45, Memory fit 24.0/25, Speed 14.5/15, Memory use 15.0/15Aya Vision 32BCohere · 33BQ4_K_M23.4 GB37.3 tok/sTight fit
79 ptsGreat (A) · 79 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2BQ8_011.7 GB76.9 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15Granite 4.1 8BIBM · 8.8BQ8_012.5 GB71.7 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15Qwen3.5 4BAlibaba · 4.7BF1611.4 GB62.3 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15MiniCPM-V 4.5 8BOpenBMB · 8.7BQ8_012.2 GB72.4 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 23.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral Small 22B (2409)Mistral AI · 22BQ5_K_M19.5 GB45.9 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)Q8_018.7 GB131 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)F1618.8 GB96.8 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)Q8_019.4 GB225 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral Nemo 12B InstructMistral AI · 12BQ8_016.1 GB51.6 tok/sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15Qwen3 8BAlibaba · 8.2BQ8_011.7 GB76.9 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Nemotron Nano 9B v2NVIDIA · 8.9BQ8_011.4 GB70.9 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15GLM-Z1 9B (0414)Zhipu AI · 9.4BQ8_012.1 GB67.0 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15Agents-A1 4BInternScience · 4.5BF1611.1 GB63.9 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 27.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15TMax 4BAi2 · 4.2BF1610.5 GB69.0 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active)Q8_019.4 GB105 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Pixtral 12B (2409)Mistral AI · 12BQ8_016.3 GB50.8 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15MiMo-VL 7B RLXiaomi · 8.3BQ8_011.8 GB75.8 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 23.3/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)Q2_K21.5 GB339 tok/sTight fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15InternLM2.5 20B ChatShanghai AI Lab · 20BQ6_K19.7 GB43.2 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15Seed-Coder 8B ReasoningByteDance · 8.3BQ8_011.6 GB76.4 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15Mage-VL 4.7BMicrosoft · 4.7BF1612.5 GB61.2 tok/sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.9/15Ministral 3 8BMistral AI · 8.9BQ8_012.4 GB70.6 tok/sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15Falcon 3 10B InstructTII · 10BQ8_014.1 GB61.1 tok/sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15Fara 1.5 4BMicrosoft · 4.5BF1611.1 GB63.9 tok/sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15Seed-Coder 8B InstructByteDance · 8.3BQ8_011.6 GB76.4 tok/sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15MiMo 7B RLXiaomi · 7.8BQ8_011.3 GB80.4 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15EXAONE Deep 7.8BLG AI Research · 7.8BQ8_011.2 GB80.6 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Qwen3 4B Thinking 2507Alibaba · 4.0BF1611.0 GB72.2 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15Qwen3-VL 4B InstructAlibaba · 4.4BF1611.9 GB65.4 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)Q8_019.0 GB105 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-3 Medium (14B)Microsoft · 14BQ8_017.4 GB45.1 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Phi-3 Medium 128K InstructMicrosoft · 14BQ8_018.3 GB45.1 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15InternVL3 8BShanghai AI Lab · 7.9BQ8_010.7 GB79.3 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0BQ8_011.4 GB78.4 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15Gemma 2 9B ITGoogle · 9.2BQ8_013.2 GB68.2 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 21.2/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)Q3_K_M23.4 GB121 tok/sTight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15GLM-4 9B 0414Zhipu AI · 9.4BQ8_012.1 GB67.0 tok/sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15Falcon-H1R 7BTII · 7.6BQ8_010.2 GB83.0 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Qwen3 4B Instruct 2507Alibaba · 4.0BF1611.0 GB72.2 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Olmo 3 7B ThinkAi2 · 7.3BQ8_011.0 GB86.3 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Granite 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)F1615.7 GB145 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OLMo 2 13B InstructAi2 · 14BQ8_019.7 GB45.9 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15Qwen2.5 Coder 7B InstructAlibaba · 7.6BQ8_010.3 GB82.7 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15MiniCPM4 8BOpenBMB · 8.2BQ8_010.7 GB76.9 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 21.4/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15Yi 1.5 34B Chat01.AI · 34BQ4_K_M23.8 GB36.0 tok/sTight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15MiniCPM-o 2.6 8BOpenBMB · 8.7BQ8_011.5 GB72.7 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15OpenReasoning Nemotron 7BNVIDIA · 7.6BQ8_010.3 GB82.7 tok/sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Qwen2.5-VL 7B InstructAlibaba · 8.3BQ8_011.1 GB76.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.1/15Qwen2.5-Omni 7BAlibaba · 11BQ8_013.6 GB58.7 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15Hunyuan 7B InstructTencent · 7.5BQ8_010.8 GB84.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15InternLM2 Chat 20BShanghai AI Lab · 20BQ6_K19.7 GB43.2 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.0/15GLM-4 9B Chat 1MZhipu AI · 9.5BQ8_012.5 GB66.4 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15InternLM3 8B InstructShanghai AI Lab · 8.8BQ8_011.5 GB71.6 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15InternVL2.5 8BShanghai AI Lab · 8.1BQ8_011.4 GB78.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15DeepSeek R1 Distill Llama 8BDeepSeek · 8.0BQ8_011.4 GB78.4 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15Qwen2.5 7B InstructAlibaba · 7.6BQ8_010.3 GB82.7 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.5/15Phi-4 Multimodal InstructMicrosoft · 5.6BF1614.0 GB52.1 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15GLM-4 9B Chat (2024)Zhipu AI · 9.4BQ8_012.1 GB67.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Fara 7BMicrosoft · 8.3BQ8_011.1 GB76.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Qwen3 4BAlibaba · 4.0BF1611.0 GB72.2 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Olmo 3 7B InstructAi2 · 7.3BQ8_011.0 GB86.3 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek Prover V2 7BDeepSeek · 6.9BF1619.6 GB42.0 tok/sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)Q8_018.7 GB131 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15StarCoder2 15B InstructBigCode · 16BQ8_019.4 GB39.5 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15InternLM2 Math Plus 20BShanghai AI Lab · 20BQ6_K19.7 GB43.2 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.4/15Granite 4.2 3BIBM · 3.7BF169.8 GB79.3 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.9/15Llama 3.2 11B Vision InstructMeta · 11BQ8_014.5 GB59.0 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Hermes 3 (Llama 3.1 8B)Nous Research · 8.0BQ8_011.4 GB78.4 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Llama 3.1 8B InstructMeta · 8.0BQ8_011.4 GB78.4 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.8/15Apertus v1.5 8BSwiss AI · 8.9BQ8_012.3 GB70.8 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15Qwen2.5 7B Instruct 1MAlibaba · 7.6BQ8_010.3 GB82.7 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 18.8/45, Memory fit 24.0/25, Speed 14.6/15, Memory use 15.0/15Qwen1.5 32B ChatAlibaba · 33BQ4_K_M23.8 GB38.1 tok/sTight fit
72 ptsGreat (A) · 72 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15CodeGeeX4 All 9BZhipu AI · 9.4BQ8_012.1 GB67.0 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15Falcon-H1 7B InstructTII · 7.6BQ8_010.2 GB83.0 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)F1618.6 GB96.8 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral 7B Instruct v0.3Mistral AI · 7.3BF1617.4 GB40.0 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15Granite 3.2 8B InstructIBM · 8.2BQ8_011.8 GB77.1 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15Granite 3.3 8BIBM · 8.2BQ8_011.8 GB77.1 tok/sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 21.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.4/15MiniCPM-V 2.6 8BOpenBMB · 8.1BQ8_010.9 GB77.8 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.5/15Nemotron 3 Nano 4BNVIDIA · 4.0BF169.9 GB73.1 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15Ministral 8B (2410)Mistral AI · 8.0BQ8_011.5 GB78.5 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0BQ8_011.4 GB78.4 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0BQ8_011.4 GB78.4 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Tülu 3 8BAi2 · 8.0BQ8_011.4 GB78.4 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek Coder 33B InstructDeepSeek · 33BQ3_K_M20.2 GB48.0 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LLaVA 1.6 34BLLaVA · 35BQ3_K_M19.8 GB46.0 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15CogVLM2 Llama 3 Chat 19BZhipu AI · 20BQ5_K_M19.9 GB52.4 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15Nous Hermes 2 SOLAR 10.7BNous Research · 11BQ8_014.0 GB58.7 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15SOLAR 10.7B InstructUpstage · 11BQ8_014.0 GB58.7 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15EXAONE 3.5 7.8BLG AI Research · 7.8BQ8_011.2 GB80.6 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.4/15Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5BF1611.9 GB64.4 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Hermes 2 Pro Mistral 7BNous Research · 7.2BF1617.4 GB40.1 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Starling LM 7B BetaNexusflow · 7.2BF1617.4 GB40.1 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.3/15Granite 3.1 8B InstructIBM · 8.2BQ8_011.8 GB77.1 tok/sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 16.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Granite Code 20B InstructIBM · 20BQ6_K18.5 GB42.8 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15Falcon 3 7B InstructTII · 7.5BQ8_010.6 GB84.4 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8BF1610.6 GB75.6 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15InternVL2 8BShanghai AI Lab · 8.1BQ8_011.4 GB78.0 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OpenChat 3.5 (0106)OpenChat · 7.2BF1617.4 GB40.1 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0BQ8_011.4 GB78.4 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Hermes 2 Pro Llama 3 8BNous Research · 8.0BQ8_011.4 GB78.4 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15OpenChat 3.6 8BOpenChat · 8.0BQ8_011.4 GB78.4 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Aya Vision 8BCohere · 8.6BQ8_011.3 GB73.0 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6BQ8_010.3 GB82.7 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15Gemma 3n E4BGoogle · 7.9BQ8_010.3 GB80.2 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.6/15Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4BQ8_012.1 GB74.9 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15Gemma 3 4B ITGoogle · 4.3BF1610.6 GB67.5 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15Granite Code 34B InstructIBM · 34BQ4_K_M22.7 GB36.7 tok/sTight fit
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Qwen2-VL 7B InstructAlibaba · 8.3BQ8_011.1 GB76.0 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 16.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)Q2_K21.6 GB78.8 tok/sTight fit
70 ptsGood (B) · 70 of 100 points: Model quality 17.1/45, Memory fit 24.0/25, Speed 14.2/15, Memory use 15.0/15Yi 34B Chat01.AI · 34BQ4_K_M23.8 GB36.0 tok/sTight fit
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek Coder 6.7B InstructDeepSeek · 6.7BF1619.6 GB43.1 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mathstral 7BMistral AI · 7.3BF1617.4 GB40.0 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral 7B Instruct v0.2Mistral AI · 7.2BF1617.4 GB40.1 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Nous Hermes 2 Mistral 7B DPONous Research · 7.2BF1617.4 GB40.1 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OpenChat 3.5 (1210)OpenChat · 7.2BF1617.4 GB40.1 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15Phi-3.5 Mini InstructMicrosoft · 3.8BF1612.7 GB76.0 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 15.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen1.5 14B ChatAlibaba · 14BQ6_K20.1 GB60.6 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15Phi-3 Small 8K InstructMicrosoft · 7.4BQ8_010.7 GB85.2 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15Command R7BCohere · 8.0BQ8_010.7 GB78.4 tok/sRuns well
70 ptsGood (B) · 70 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15MedGemma 4B ITGoogle · 4.3BF1610.6 GB67.5 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.1/15Phi-4 Mini (3.8B)Microsoft · 3.8BF1610.6 GB75.6 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.8/15Phi-3.5 Vision InstructMicrosoft · 4.2BF1613.3 GB70.0 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15Hunyuan 4B InstructTencent · 4.2BF1611.4 GB68.8 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Llama 3 8B InstructMeta · 8.0BQ8_011.4 GB78.4 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15Ministral 3 3BMistral AI · 3.9BF1610.4 GB75.4 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)Q2_K22.6 GB84.7 tok/sTight fit
69 ptsGood (B) · 69 of 100 points: Model quality 15.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15Mixtral 8x7B InstructMistral AI · 47B (12.9B active)Q2_K21.6 GB78.8 tok/sTight fit
69 ptsGood (B) · 69 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.9/15Qwen2 7B InstructAlibaba · 7.6BQ8_010.3 GB82.7 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 20.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15Granite 4.1 3BIBM · 3.4BF169.3 GB85.4 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 16.2/45, Memory fit 24.0/25, Speed 14.4/15, Memory use 15.0/15Code Llama 34B InstructMeta · 34BQ4_K_M24.0 GB36.7 tok/sTight fit
69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15Yi Coder 9B Chat01.AI · 8.8BQ8_012.0 GB71.3 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OpenHermes 2.5 Mistral 7BTeknium · 7.2BF1617.4 GB40.1 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Starling LM 7B AlphaBerkeley · 7.2BF1617.4 GB40.1 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15CodeGemma 7BGoogle · 8.5BQ8_014.6 GB73.8 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15StarCoder2 15B (base)BigCode · 16BQ8_019.4 GB39.5 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15AFM 4.5BArcee AI · 4.6BF1611.6 GB62.8 tok/sRuns well
69 ptsGood (B) · 69 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15Command R7B ArabicCohere · 8.0BQ8_010.7 GB78.4 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15Apertus 8B InstructSwiss AI · 8.1BQ8_011.4 GB78.2 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Aya Expanse 8BCohere · 8.0BQ8_011.4 GB78.4 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15Granite 3.0 8B InstructIBM · 8.2BQ8_011.1 GB77.1 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15InternLM2.5 7B ChatShanghai AI Lab · 7.7BQ8_011.1 GB81.4 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15Gemma 3n E2BGoogle · 5.4BF1612.8 GB53.4 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Mistral 7B Instruct v0.1Mistral AI · 7.2BF1617.4 GB40.1 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15SQLCoder 7B v2Defog · 6.7BF1619.6 GB43.1 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15Phi-3 Mini 128K InstructMicrosoft · 3.8BF1612.7 GB76.0 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 13.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Code Llama 13B InstructMeta · 13BQ6_K19.2 GB65.9 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.8/15Phi-3 Vision 128K InstructMicrosoft · 4.2BF1613.3 GB70.0 tok/sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0BQ8_011.4 GB78.4 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15Voxtral Mini 3BMistral AI · 4.7BF1612.2 GB62.0 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15Jamba Reasoning 3BAI21 Labs · 3.2BF168.2 GB90.7 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15LFM2.5-VL 3BLiquid AI · 3.1BF168.2 GB93.0 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Neural Chat 7B v3.3Intel · 7.2BF1617.4 GB40.1 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Orca 2 13BMicrosoft · 13BQ8_019.0 GB48.4 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.9/15StableLM 2 12B ChatStability AI · 12BQ8_015.5 GB51.9 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15OLMo 2 7B InstructAi2 · 7.3BQ8_011.7 GB86.3 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15Yi 1.5 9B Chat01.AI · 8.8BQ8_011.6 GB71.3 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15EXAONE 3.0 7.8B InstructLG AI Research · 7.8BQ8_010.6 GB80.6 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.4/15North Micro VisionCohere · 2.5BF167.7 GB117 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.2/15SmolLM3 3BHugging Face · 3.1BF168.6 GB94.3 tok/sRuns well
67 ptsGood (B) · 67 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.0/15Zamba2 7B InstructZyphra · 7.4BQ8_010.4 GB85.6 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15RecurrentGemma 9B ITGoogle · 9.6BQ8_012.1 GB65.4 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.8/15MiniCPM3 4BOpenBMB · 4.1BF1610.2 GB71.3 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15Granite 4.0 Micro (3B)IBM · 3.4BF169.3 GB85.4 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 19.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15LFM2.5 2.6BLiquid AI · 2.7BF167.3 GB108 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.6/15Phi-3 Mini 4K InstructMicrosoft · 3.8BF1611.1 GB76.0 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Baichuan 2 13B ChatBaichuan · 14BQ8_019.9 GB45.3 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)Q8_020.1 GB112 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Llama 2 13B ChatMeta · 13BQ8_019.0 GB48.4 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)F1616.2 GB112 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15WizardMath 7B v1.1WizardLM · 7.2BF1617.4 GB40.1 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Zephyr 7B BetaHugging Face · 7.2BF1617.4 GB40.1 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15StarCoder 15BBigCode · 16BQ8_018.7 GB39.8 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15Gemma 1.1 7B ITGoogle · 8.5BQ8_014.6 GB73.8 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)F169.0 GB242 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15Jamba2 3BAI21 Labs · 3.0BF167.9 GB95.8 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15Falcon3 Mamba 7B InstructTII · 7.3BQ8_09.5 GB86.6 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.9/15Aya 23 8BCohere · 8.0BQ8_011.4 GB78.4 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15Yi 1.5 6B Chat01.AI · 6.1BF1614.2 GB47.9 tok/sRuns well
66 ptsGood (B) · 66 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.7/15Qwen2.5-Omni 3BAlibaba · 5.5BF1613.2 GB52.4 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 32.5/45, Memory fit 4.0/25, Speed 14.5/15, Memory use 15.0/15Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active)Q3_K_M41.0 GB37.2 tok/sHeavy offload
65 ptsGood (B) · 65 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.7/15Qwen2.5-Math 7B InstructAlibaba · 7.6BQ8_010.1 GB82.7 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 32.5/45, Memory fit 4.0/25, Speed 14.3/15, Memory use 15.0/15Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)Q3_K_M41.8 GB36.4 tok/sHeavy offload
65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Code Llama 7B InstructMeta · 6.7BF1619.6 GB43.1 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)Q8_018.6 GB117 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15StarCoder2 7BBigCode · 7.2BF1616.7 GB40.5 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.0/15Gemma 7B ITGoogle · 8.5BQ8_014.6 GB73.8 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.1/15Granite Code 8B Instruct (128K)IBM · 8.1BQ8_011.5 GB78.2 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15Qwen1.5 7B ChatAlibaba · 7.7BQ8_014.3 GB81.6 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15Codestral Mamba 7BMistral AI · 7.3BQ8_09.6 GB86.4 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 31.8/45, Memory fit 4.0/25, Speed 14.3/15, Memory use 15.0/15Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active)Q3_K_M41.8 GB36.4 tok/sHeavy offload
65 ptsGood (B) · 65 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.7/15InternLM2 Math Plus 7BShanghai AI Lab · 7.7BQ8_011.1 GB81.4 tok/sRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 17.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.9/15Granite 4.0 H MicroIBM · 3.2BF168.2 GB91.0 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LLaVA 1.5 13BLLaVA · 13BQ8_019.3 GB47.2 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Orca 2 7BMicrosoft · 6.7BF1617.4 GB43.1 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15WizardLM 13B v1.2WizardLM · 13BQ8_019.0 GB48.4 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15Llama 3.2 3B InstructMeta · 3.2BF169.2 GB90.4 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15Qwen2.5-VL 3B InstructAlibaba · 3.8BF169.6 GB77.4 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15Falcon-H1 3B InstructTII · 3.2BF168.4 GB92.2 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15Qwen3.5 2BAlibaba · 2.3BF166.4 GB128 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15Qwen2.5 Coder 3B InstructAlibaba · 3.1BF168.3 GB93.9 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Llama 2 7B ChatMeta · 6.7BF1617.4 GB43.1 tok/sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Vicuna 13B v1.5LMSYS · 13BQ8_019.0 GB48.4 tok/sRuns well
63 ptsGood (B) · 63 of 100 points: Model quality 25.2/45, Memory fit 10.0/25, Speed 13.2/15, Memory use 15.0/15Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50BQ2_K24.4 GB31.2 tok/sRuns with offload
63 ptsGood (B) · 63 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15TMax 2BAi2 · 1.9BF165.7 GB154 tok/sRuns well
63 ptsGood (B) · 63 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.0/15Qwen2.5 3B InstructAlibaba · 3.1BF168.3 GB93.9 tok/sRuns well
63 ptsGood (B) · 63 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.8/15Hermes 3 Llama 3.2 3BNous Research · 3.2BF169.2 GB90.4 tok/sRuns well
63 ptsGood (B) · 63 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15DeepSeek LLM 7B ChatDeepSeek · 6.9BF1617.6 GB42.0 tok/sRuns well
63 ptsGood (B) · 63 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.5/15LLaVA 1.6 Mistral 7BLLaVA · 7.6BQ8_010.9 GB83.2 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 16.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15Qwen3-VL 2B InstructAlibaba · 2.1BF167.0 GB136 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.2/15Falcon Mamba 7B InstructTII · 7.3BQ8_09.5 GB86.6 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15Yi 6B Chat01.AI · 6.1BF1614.2 GB47.9 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LLaVA 1.5 7BLLaVA · 7.1BF1618.1 GB41.1 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.7/15Falcon 3 3B InstructTII · 3.2BF169.0 GB89.9 tok/sRuns well
62 ptsGood (B) · 62 of 100 points: Model quality 15.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.8/15LFM2 2.6BLiquid AI · 2.6BF167.1 GB113 tok/sRuns well
61 ptsGood (B) · 61 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15OLMo 7B InstructAi2 · 6.9BF1616.7 GB42.1 tok/sRuns well
61 ptsGood (B) · 61 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Vicuna 7B v1.5LMSYS · 6.7BF1617.4 GB43.1 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15Granite 3.2 2B InstructIBM · 2.5BF167.5 GB115 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15Granite 3.3 2BIBM · 2.5BF167.5 GB115 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.0/15EXAONE 3.5 2.4BLG AI Research · 2.4BF167.2 GB120 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.5/15Baichuan 2 7B ChatBaichuan · 7.5BQ8_011.9 GB83.9 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.3/15Nemotron Mini 4B InstructNVIDIA · 4.2BF1610.7 GB69.3 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 5.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Falcon 40B InstructTII · 42BQ2_K18.8 GB48.6 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.5/15Qwen3 1.7BAlibaba · 2.0BF166.8 GB143 tok/sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.0/15Granite Code 3B Instruct (128K)IBM · 3.5BF1611.4 GB83.4 tok/sRuns well
59 ptsGood (B) · 59 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15Granite 3.1 2B InstructIBM · 2.5BF167.5 GB115 tok/sRuns well
59 ptsGood (B) · 59 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15Gemma 2 2BGoogle · 2.6BF167.5 GB111 tok/sRuns well
59 ptsGood (B) · 59 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15Granite Vision 3.2 2BIBM · 3.0BF168.4 GB97.4 tok/sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.1/15Granite 3.0 2B InstructIBM · 2.6BF167.4 GB110 tok/sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.7/15Stable Code Instruct 3BStability AI · 2.8BF1610.1 GB104 tok/sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 14.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15LFM2.5 1.2B InstructLiquid AI · 1.2BF164.2 GB248 tok/sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15SmolVLM2 2.2B InstructHugging Face · 2.3BF167.9 GB129 tok/sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.7/15EXAONE 4.0 1.2BLG AI Research · 1.3BF164.9 GB227 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Falcon 7B InstructTII · 7.2BF1616.3 GB40.2 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)F168.9 GB181 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.6/15SmolVLM 2.2B InstructHugging Face · 2.3BF167.9 GB129 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.6/15Granite 4.0 H 1BIBM · 1.5BF164.8 GB199 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.2/15Zamba2 2.7B InstructZyphra · 2.7BF167.5 GB109 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15DeepScaleR 1.5B PreviewAgentica · 1.8BF165.6 GB163 tok/sRuns well
57 ptsUsable (C) · 57 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.2/15Qwen2-VL 2B InstructAlibaba · 2.2BF166.5 GB131 tok/sRuns well
56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15Qwen2.5 Coder 1.5B InstructAlibaba · 1.5BF165.1 GB189 tok/sRuns well
56 ptsUsable (C) · 56 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15Falcon-H1 1.5B InstructTII · 1.6BF165.1 GB187 tok/sRuns well
56 ptsUsable (C) · 56 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.5/15Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)F168.8 GB181 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15StarCoder2 3BBigCode · 3.0BF168.1 GB95.8 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15LFM2 1.2BLiquid AI · 1.2BF164.2 GB248 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)Q2_K25.2 GB41.3 tok/sRuns with offload
55 ptsUsable (C) · 55 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15Qwen2.5 1.5B InstructAlibaba · 1.5BF165.1 GB189 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 10.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15LFM2-VL 1.6BLiquid AI · 1.6BF165.1 GB184 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 10.2/15InternLM 7BShanghai AI Lab · 7.3BQ8_010.6 GB86.1 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.4/15StableLM Zephyr 3BStability AI · 2.8BF168.7 GB104 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15Hunyuan 1.8B InstructTencent · 1.8BF165.9 GB162 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.6/15SmolLM2 1.7B InstructHugging Face · 1.7BF166.8 GB170 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8BF165.6 GB163 tok/sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 11.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15Qwen3.5 0.8BAlibaba · 0.9BF163.6 GB334 tok/sRuns well
54 ptsUsable (C) · 54 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.7/15Phi-2 2.7BMicrosoft · 2.8BF168.0 GB104 tok/sRuns well
54 ptsUsable (C) · 54 of 100 points: Model quality 24.6/45, Memory fit 4.0/25, Speed 11.0/15, Memory use 15.0/15Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K43.5 GB21.7 tok/sHeavy offload
54 ptsUsable (C) · 54 of 100 points: Model quality 9.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.4/15Llama 3.2 1B InstructMeta · 1.2BF164.5 GB234 tok/sRuns well
54 ptsUsable (C) · 54 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15InternLM2.5 1.8B ChatShanghai AI Lab · 1.9BF166.4 GB154 tok/sRuns well
54 ptsUsable (C) · 54 of 100 points: Model quality 31.0/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Llama 3.3 70B InstructMeta · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
53 ptsUsable (C) · 53 of 100 points: Model quality 23.9/45, Memory fit 4.0/25, Speed 11.0/15, Memory use 15.0/15Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K43.5 GB21.7 tok/sHeavy offload
53 ptsUsable (C) · 53 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.8/15Qwen2.5-Math 1.5B InstructAlibaba · 1.5BF165.0 GB189 tok/sRuns well
53 ptsUsable (C) · 53 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 6.8/15, Memory use 15.0/15Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)Q3_K_M42.3 GB8.2 tok/sHeavy offload
53 ptsUsable (C) · 53 of 100 points: Model quality 30.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Kimi Dev 72BMoonshot AI · 73BQ3_K_M40.1 GB3.0 tok/sHeavy offload
53 ptsUsable (C) · 53 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.1/15Yi Coder 1.5B Chat01.AI · 1.5BF166.4 GB196 tok/sRuns well
53 ptsUsable (C) · 53 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15CodeGemma 2BGoogle · 2.5BF167.0 GB116 tok/sRuns well
52 ptsUsable (C) · 52 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.5/15Falcon 3 1B InstructTII · 1.7BF165.7 GB174 tok/sRuns well
52 ptsUsable (C) · 52 of 100 points: Model quality 9.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.7/15Gemma 3 1BGoogle · 1.0BF163.9 GB290 tok/sRuns well
52 ptsUsable (C) · 52 of 100 points: Model quality 7.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.9/15Qwen2 1.5B InstructAlibaba · 1.5BF165.1 GB189 tok/sRuns well
52 ptsUsable (C) · 52 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 6.7/15Gemma 2B ITGoogle · 2.5BF167.0 GB116 tok/sRuns well
51 ptsUsable (C) · 51 of 100 points: Model quality 25.2/45, Memory fit 4.0/25, Speed 7.7/15, Memory use 15.0/15Solar Open 100BUpstage · 103B (12.0B active)Q2_K44.5 GB10.5 tok/sHeavy offload
51 ptsUsable (C) · 51 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.4/15SmolLM 1.7B InstructHugging Face · 1.7BF165.6 GB170 tok/sRuns well
51 ptsUsable (C) · 51 of 100 points: Model quality 17.0/45, Memory fit 10.0/25, Speed 9.6/15, Memory use 15.0/15Command R 35B (v01)Cohere · 35BQ2_K26.5 GB16.4 tok/sRuns with offload
51 ptsUsable (C) · 51 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.1/15OLMo 2 1B InstructAi2 · 1.5BF165.3 GB196 tok/sRuns well
51 ptsUsable (C) · 51 of 100 points: Model quality 8.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.3/15LFM2 700MLiquid AI · 0.7BF163.4 GB392 tok/sRuns well
51 ptsUsable (C) · 51 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.9/15DeepSeek Coder 1.3B InstructDeepSeek · 1.4BF166.1 GB215 tok/sRuns well
51 ptsUsable (C) · 51 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Hermes 4 70BNous Research · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
51 ptsUsable (C) · 51 of 100 points: Model quality 23.6/45, Memory fit 4.0/25, Speed 8.5/15, Memory use 15.0/15Sarvam 105BSarvam AI · 106B (10.0B active)Q2_K44.5 GB13.0 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 28.0/45, Memory fit 4.0/25, Speed 3.8/15, Memory use 15.0/15InternVL3 78BShanghai AI Lab · 78BQ3_K_M42.9 GB2.6 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 27.6/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Qwen2.5 72B InstructAlibaba · 73BQ3_K_M40.1 GB3.0 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 27.6/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Qwen2.5-VL 72B InstructAlibaba · 73BQ3_K_M40.5 GB2.9 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 27.2/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15DeepSeek R1 Distill Llama 70BDeepSeek · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 27.2/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Tülu 3 70BAi2 · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
50 ptsUsable (C) · 50 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.1/15Qwen3 0.6BAlibaba · 0.8BF164.2 GB387 tok/sRuns well
50 ptsUsable (C) · 50 of 100 points: Model quality 15.8/45, Memory fit 10.0/25, Speed 9.6/15, Memory use 15.0/15Aya 23 35BCohere · 35BQ2_K26.5 GB16.4 tok/sRuns with offload
50 ptsUsable (C) · 50 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15StableLM 2 1.6B ChatStability AI · 1.6BF165.9 GB177 tok/sRuns well
50 ptsUsable (C) · 50 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 5.7/15StableLM 2 Zephyr 1.6BStability AI · 1.6BF165.9 GB177 tok/sRuns well
49 ptsUsable (C) · 49 of 100 points: Model quality 26.5/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Llama 3.1 70B InstructMeta · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
49 ptsUsable (C) · 49 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.9/15Falcon-H1 0.5B InstructTII · 0.5BF163.0 GB558 tok/sRuns well
48 ptsUsable (C) · 48 of 100 points: Model quality 25.7/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Hermes 3 (Llama 3.1 70B)Nous Research · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
48 ptsUsable (C) · 48 of 100 points: Model quality 18.3/45, Memory fit 10.0/25, Speed 5.6/15, Memory use 15.0/15Qwen2.5-Math 72B InstructAlibaba · 73BQ2_K32.2 GB5.6 tok/sRuns with offload
48 ptsUsable (C) · 48 of 100 points: Model quality 6.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15LFM2.5 350MLiquid AI · 0.4BF162.6 GB829 tok/sRuns well
48 ptsUsable (C) · 48 of 100 points: Model quality 25.7/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15QVQ 72B PreviewAlibaba · 73BQ3_K_M40.5 GB2.9 tok/sHeavy offload
48 ptsUsable (C) · 48 of 100 points: Model quality 24.9/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Llama 3.1 Nemotron 70B InstructNVIDIA · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
48 ptsUsable (C) · 48 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15LFM2-VL 450MLiquid AI · 0.5BF162.8 GB645 tok/sRuns well
48 ptsUsable (C) · 48 of 100 points: Model quality 24.9/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Apertus v1.5 70BSwiss AI · 72BQ3_K_M39.8 GB3.0 tok/sHeavy offload
47 ptsUsable (C) · 47 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15LFM2 350MLiquid AI · 0.4BF162.6 GB829 tok/sRuns well
47 ptsUsable (C) · 47 of 100 points: Model quality 5.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15Granite 4.0 H 350MIBM · 0.3BF162.5 GB854 tok/sRuns well
47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.0/15SmolVLM 500M InstructHugging Face · 0.5BF163.2 GB569 tok/sRuns well
47 ptsUsable (C) · 47 of 100 points: Model quality 24.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Qwen2 72B InstructAlibaba · 73BQ3_K_M40.1 GB3.0 tok/sHeavy offload
47 ptsUsable (C) · 47 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15Qwen2.5 0.5B InstructAlibaba · 0.5BF162.9 GB592 tok/sRuns well
47 ptsUsable (C) · 47 of 100 points: Model quality 24.2/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Qwen2-VL 72B InstructAlibaba · 73BQ3_K_M40.5 GB2.9 tok/sHeavy offload
47 ptsUsable (C) · 47 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.5/15Hunyuan 0.5B InstructTencent · 0.5BF163.7 GB538 tok/sRuns well
46 ptsUsable (C) · 46 of 100 points: Model quality 4.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15LFM2.5 230MLiquid AI · 0.2BF162.3 GB1,262 tok/sRuns well
46 ptsUsable (C) · 46 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.9/15TinyLlama 1.1B ChatTinyLlama · 1.1BF164.0 GB264 tok/sRuns well
46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15Qwen2.5 Coder 0.5B InstructAlibaba · 0.5BF162.9 GB592 tok/sRuns well
46 ptsUsable (C) · 46 of 100 points: Model quality 3.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15SmolLM2 360M InstructHugging Face · 0.4BF162.9 GB806 tok/sRuns well
45 ptsUsable (C) · 45 of 100 points: Model quality 22.7/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Apertus 70B InstructSwiss AI · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.8/15Qwen2 0.5B InstructAlibaba · 0.5BF162.9 GB592 tok/sRuns well
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.6/15ERNIE 4.5 0.3BBaidu · 0.4BF162.7 GB806 tok/sRuns well
45 ptsUsable (C) · 45 of 100 points: Model quality 21.9/45, Memory fit 4.0/25, Speed 4.2/15, Memory use 15.0/15Llama 3 70B InstructMeta · 71BQ3_K_M39.1 GB3.2 tok/sHeavy offload
45 ptsUsable (C) · 45 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.4/15SmolVLM 256M InstructHugging Face · 0.3BF162.5 GB1,117 tok/sRuns well
44 ptsUsable (C) · 44 of 100 points: Model quality 2.7/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.3/15Gemma 3 270MGoogle · 0.3BF162.4 GB1,075 tok/sRuns well
44 ptsUsable (C) · 44 of 100 points: Model quality 13.9/45, Memory fit 10.0/25, Speed 6.1/15, Memory use 15.0/15Code Llama 70B InstructMeta · 69BQ2_K30.7 GB6.6 tok/sRuns with offload
44 ptsUsable (C) · 44 of 100 points: Model quality 2.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.5/15SmolLM 360M InstructHugging Face · 0.4BF162.6 GB806 tok/sRuns well
43 ptsUsable (C) · 43 of 100 points: Model quality 1.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.2/15SmolLM2 135M InstructHugging Face · 0.1BF162.2 GB2,233 tok/sRuns well
43 ptsUsable (C) · 43 of 100 points: Model quality 20.8/45, Memory fit 4.0/25, Speed 4.1/15, Memory use 15.0/15Llama 3.2 90B Vision InstructMeta · 89BQ2_K40.6 GB3.0 tok/sHeavy offload
43 ptsUsable (C) · 43 of 100 points: Model quality 12.6/45, Memory fit 10.0/25, Speed 6.3/15, Memory use 15.0/15DeepSeek LLM 67B ChatDeepSeek · 67BQ2_K30.4 GB7.0 tok/sRuns with offload
43 ptsUsable (C) · 43 of 100 points: Model quality 1.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.0/15Falcon-H1 Tiny 90M InstructTII · 0.1BF162.1 GB3,226 tok/sRuns well
42 ptsUsable (C) · 42 of 100 points: Model quality 0.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.0/15SmolLM 135M InstructHugging Face · 0.1BF162.1 GB2,233 tok/sRuns well
42 ptsUsable (C) · 42 of 100 points: Model quality 11.3/45, Memory fit 10.0/25, Speed 6.1/15, Memory use 15.0/15Llama 2 70B ChatMeta · 69BQ2_K30.7 GB6.6 tok/sRuns with offload
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 0.0/15gpt-oss 120BOpenAI · 117B (5.1B active)MXFP468.7 GB—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 0.0/15MiMo V2.6 Pro (1T-A42B)Xiaomi · 1,024B (42.0B active)Q2_K412 GB—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 0.0/15Qwen3.8 Max (2.4T-A95B)Alibaba · 2,446B (95.0B active)Q2_K981 GB—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 0.0/15Kimi K3 (2.8T)Moonshot AI · 2,780B (104.0B active)Q2_K1,114 GB—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 0.0/15GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K304 GB—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 0.0/15MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active)Q2_K126 GB—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 0.0/15DeepSeek V4 Pro (1.6T-A49B)DeepSeek · 1,651B (49.0B active)Q2_K663 GB—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 0.0/15Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active)Q2_K74.0 GB—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 0.0/15GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K304 GB—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 0.0/15Hunyuan Hy4 Preview (780B)Tencent · 780B (55.0B active)Q2_K315 GB—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 0.0/15Kimi K2.6 (1T)Moonshot AI · 1,027B (32.0B active)Q2_K413 GB—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 0.0/15GLM-5.3 Flash (320B-A18B)Zhipu AI · 321B (18.0B active)Q2_K130 GB—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 0.0/15GLM-5.1 (744B-A40B)Zhipu AI · 754B (40.0B active)Q2_K304 GB—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 0.0/15DeepSeek V4 Pro (April 2026)DeepSeek · 1,599B (49.0B active)Q2_K642 GB—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 0.0/15Qwen3.5 397B-A17BAlibaba · 403B (17.0B active)Q2_K163 GB—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 0.0/15MiniMax M3 (427B)MiniMax · 427B (25.0B active)Q2_K174 GB—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 0.0/15GLM-5 (744B-A40B)Zhipu AI · 754B (40.0B active)Q2_K304 GB—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 0.0/15Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active)Q2_K124 GB—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 0.0/15Kimi K2.5 (1T)Moonshot AI · 1,027B (32.0B active)Q2_K413 GB—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 0.0/15Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active)Q2_K413 GB—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 0.0/15DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active)Q2_K124 GB—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 0.0/15Ornith 1.5 397B-A17BDeepReinforce · 403B (17.0B active)Q2_K163 GB—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 0.0/15DeepSeek V3.2 (671B)DeepSeek · 685B (37.0B active)Q2_K277 GB—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 0.0/15GLM-4.7 (355B-A32B)Zhipu AI · 358B (32.0B active)Q2_K148 GB—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 0.0/15MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K95.4 GB—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 0.0/15Nemotron 3 Ultra 550B-A55BNVIDIA · 561B (55.0B active)Q2_K226 GB—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 0.0/15DeepSeek R1 0528 (671B)DeepSeek · 685B (37.0B active)Q2_K276 GB—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 0.0/15Kimi K2 Thinking (1T)Moonshot AI · 1,026B (32.0B active)Q2_K413 GB—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 0.0/15DeepSeek V3.2 ExpDeepSeek · 685B (37.0B active)Q2_K277 GB—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 0.0/15MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K95.4 GB—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 0.0/15DeepSeek R1 (671B)DeepSeek · 671B (37.0B active)Q2_K271 GB—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 0.0/15DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active)Q2_K119 GB—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 0.0/15Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)Q2_K52.0 GB—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 0.0/15Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active)Q2_K82.0 GB—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 0.0/15DeepSeek V3.1 TerminusDeepSeek · 685B (37.0B active)Q2_K276 GB—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 0.0/15DeepSeek V3.1 (671B)DeepSeek · 685B (37.0B active)Q2_K276 GB—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 0.0/15Kimi K2 Instruct 0905 (1T)Moonshot AI · 1,026B (32.0B active)Q2_K413 GB—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 0.0/15MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K95.4 GB—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 0.0/15Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active)Q2_K97.4 GB—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 0.0/15Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active)Q2_K196 GB—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 0.0/15MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active)Q2_K126 GB—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 0.0/15Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active)Q2_K404 GB—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 0.0/15Mistral Large 3 (675B)Mistral AI · 675B (41.0B active)Q2_K272 GB—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 0.0/15Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active)Q2_K97.4 GB—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 0.0/15Solar Open 2 250BUpstage · 250B (15.0B active)Q2_K104 GB—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 0.0/15Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active)Q2_K413 GB—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 0.0/15MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K95.4 GB—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 0.0/15Qwen3-VL 235B-A22B InstructAlibaba · 236B (22.0B active)Q2_K97.6 GB—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 0.0/15K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active)Q2_K97.1 GB—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 0.0/15LongCat Flash Chat (560B)Meituan · 562B (27.0B active)Q2_K227 GB—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 0.0/15Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active)Q2_K51.3 GB—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 0.0/15Qwen3 235B-A22BAlibaba · 235B (22.0B active)Q2_K97.4 GB—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 0.0/15Devstral 2 (123B)Mistral AI · 125BQ2_K54.8 GB—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 0.0/15InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active)Q2_K99.7 GB—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 0.0/15Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active)Q2_K50.4 GB—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 0.0/15Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 253BQ2_K107 GB—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 0.0/15Baichuan M3 235B-A22BBaichuan · 235B (22.0B active)Q2_K97.4 GB—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 0.0/15GLM-4.6 (355B-A32B)Zhipu AI · 357B (32.0B active)Q2_K148 GB—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 0.0/15DeepSeek V3 0324 (671B)DeepSeek · 685B (37.0B active)Q2_K276 GB—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 0.0/15GLM-4.6VZhipu AI · 108B (12.0B active)Q2_K46.4 GB—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 0.0/15MiniMax-M1 80KMiniMax · 456B (45.9B active)Q2_K185 GB—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 0.0/15Command A Reasoning (111B)Cohere · 111BQ2_K47.0 GB—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 0.0/15GLM-4.5 (355B-A32B)Zhipu AI · 358B (32.0B active)Q2_K148 GB—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 0.0/15Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active)Q2_K53.2 GB—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 0.0/15MiniMax-M1 40KMiniMax · 456B (45.9B active)Q2_K185 GB—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 0.0/15Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active)Q2_K49.7 GB—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 0.0/15Mistral Medium 3.5 (128B)Mistral AI · 128BQ2_K55.8 GB—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 0.0/15Trinity Large Thinking (400B-A13B)Arcee AI · 399B (13.0B active)Q2_K162 GB—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 0.0/15Command A (111B)Cohere · 111BQ2_K47.0 GB—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 0.0/15ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active)Q2_K124 GB—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 0.0/15GLM-4.5VZhipu AI · 108B (12.0B active)Q2_K46.4 GB—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 0.0/15Hermes 4 405BNous Research · 406BQ2_K168 GB—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 0.0/15Mistral Large 2.1 (2411)Mistral AI · 123BQ2_K53.8 GB—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 0.0/15GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)Q2_K47.5 GB—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 0.0/15Mistral Large 2 (123B)Mistral AI · 123BQ2_K54.0 GB—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 0.0/15Pixtral Large 124B (2411)Mistral AI · 124BQ2_K54.4 GB—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 0.0/15dots.llm1 Instructrednote · 143B (14.0B active)Q2_K67.2 GB—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 0.0/15MiniMax-Text-01MiniMax · 456B (45.9B active)Q2_K185 GB—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 0.0/15Tülu 3 405BAi2 · 406BQ2_K168 GB—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 0.0/15DeepSeek V3 (671B)DeepSeek · 671B (37.0B active)Q2_K271 GB—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 0.0/15DeepSeek Coder V2 (236B)DeepSeek · 236B (21.0B active)Q2_K96.7 GB—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 0.0/15Leanstral 119B-A6BMistral AI · 119B (6.5B active)Q2_K49.7 GB—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 0.0/15DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active)Q2_K96.7 GB—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 0.0/15DeepSeek V2.5 1210DeepSeek · 236B (21.0B active)Q2_K96.7 GB—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 0.0/15Llama 3.1 405B InstructMeta · 406BQ2_K168 GB—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 0.0/15Llama 4 Maverick (17B x 128E)Meta · 402B (17.0B active)Q2_K164 GB—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 0.0/15Llama 4 Scout 17B-16EMeta · 109B (17.0B active)Q2_K46.9 GB—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 0.0/15Command R+ (08-2024) 104BCohere · 104BQ2_K45.5 GB—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 0.0/15DeepSeek V2.5DeepSeek · 236B (21.0B active)Q2_K96.7 GB—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 0.0/15Jamba 1.5 LargeAI21 Labs · 399B (94.0B active)Q2_K162 GB—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 0.0/15Command R+ 104B (04-2024)Cohere · 104BQ2_K45.5 GB—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 0.0/15DeepSeek V2 ChatDeepSeek · 236B (21.0B active)Q2_K96.7 GB—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 0.0/15Mixtral 8x22B InstructMistral AI · 141B (39.0B active)Q2_K59.9 GB—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 0.0/15Qwen1.5 110B ChatAlibaba · 111BQ2_K49.0 GB—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 0.0/15Grok-1 (314B)xAI · 314B (86.0B active)Q2_K130 GB—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 0.0/15Snowflake Arctic InstructSnowflake · 479B (17.0B active)Q2_K194 GB—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 0.0/15Falcon 180B ChatTII · 180BQ2_K73.9 GB—Won't run

Image models on your NVIDIA GeForce RTX 4090

Grade · points Model Precision Memory Time per output Fit
92 ptsExcellent (S) · 92 of 100 points: Model quality 37.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15FLUX.2 [klein] 9BBlack Forest Labs · 9.1BFP819.9 GB1.6 sRuns well
90 ptsExcellent (S) · 90 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15FLUX.1 Krea [dev]Black Forest Labs · 11.9BFP819.6 GB11 sRuns well
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15FLUX.2 [klein] 4BBlack Forest Labs · 3.9BFP1618.1 GB1.0 sRuns well
89 ptsExcellent (S) · 89 of 100 points: Model quality 37.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.5/15Z-Image TurboAlibaba (Tongyi) · 6.2BQ8 GGUF13.0 GB2.9 sRuns well
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.3/45, Memory fit 25.0/25, Speed 14.4/15, Memory use 15.0/15FLUX.1 [dev]Black Forest Labs · 11.9BFP819.6 GB11 sRuns well
87 ptsExcellent (S) · 87 of 100 points: Model quality 33.5/45, Memory fit 25.0/25, Speed 14.1/15, Memory use 15.0/15FLUX.1 Fill [dev]Black Forest Labs · 11.9BFP819.6 GB11 sRuns well
86 ptsExcellent (S) · 86 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 10.7/15, Memory use 15.0/15FLUX.1 Kontext [dev]Black Forest Labs · 11.9BFP820.2 GB20 sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15FLUX.1 [schnell]Black Forest Labs · 11.9BFP819.6 GB1.8 sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 34.4/45, Memory fit 25.0/25, Speed 11.2/15, Memory use 15.0/15Chroma1-HDLodestone Rock · 8.9BFP816.4 GB18 sRuns well
85 ptsExcellent (S) · 85 of 100 points: Model quality 36.2/45, Memory fit 25.0/25, Speed 12.1/15, Memory use 12.1/15Z-ImageAlibaba (Tongyi) · 6.2BFP812.6 GB15 sRuns well
84 ptsGreat (A) · 84 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Stable Diffusion 3.5 LargeStability AI · 8.1BFP816.3 GB9.9 sRuns well
83 ptsGreat (A) · 83 of 100 points: Model quality 33.5/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 15.0/15HiDream-I1 FastHiDream.ai · 17.1BFP820.1 GB9.5 sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 30.9/45, Memory fit 25.0/25, Speed 11.8/15, Memory use 15.0/15CogView4 6BZhipu AI · 6.4BFP818.2 GB16 sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Stable Diffusion 3.5 Large TurboStability AI · 8.1BQ8 GGUF16.8 GB1.8 sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 35.3/45, Memory fit 20.0/25, Speed 11.8/15, Memory use 15.0/15HiDream-I1 DevHiDream.ai · 17.1BFP820.1 GB16 sRuns well
82 ptsGreat (A) · 82 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15KolorsKuaishou · 2.6BFP1619.8 GB4.0 sRuns well
81 ptsGreat (A) · 81 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Stable Diffusion 3.5 MediumStability AI · 2.5BFP1618.4 GB6.0 sRuns well
80 ptsGreat (A) · 80 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.2/15Lumina-Image 2.0Shanghai AI Lab · 2.6BFP1612.7 GB7.0 sRuns well
79 ptsGreat (A) · 79 of 100 points: Model quality 37.0/45, Memory fit 20.0/25, Speed 7.3/15, Memory use 15.0/15HiDream-I1 FullHiDream.ai · 17.1BFP820.1 GB43 sRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 38.5/45, Memory fit 18.0/25, Speed 7.0/15, Memory use 15.0/15FLUX.2 [dev]Black Forest Labs · 32.2BQ4 GGUF22.8 GB45 sTight fit
78 ptsGreat (A) · 78 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15Stable Diffusion 3 MediumStability AI · 2.0BFP1617.4 GB3.1 sRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 37.7/45, Memory fit 20.0/25, Speed 4.5/15, Memory use 15.0/15Qwen-Image 2512Alibaba · 20.4BQ4 GGUF18.6 GB1.9 minRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.4/15Stable CascadeStability AI · 5.2BFP1614.0 GB5.0 sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 29.1/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 9.9/15OmniGen2BAAI (VectorSpaceLab) · 4.0BFP810.3 GB14 sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Juggernaut XL v9RunDiffusion · 2.6BFP168.9 GB4.5 sRuns well
76 ptsGreat (A) · 76 of 100 points: Model quality 27.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15RealVisXL V5.0SG161222 · 2.6BFP168.9 GB4.5 sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 36.0/45, Memory fit 20.0/25, Speed 4.7/15, Memory use 15.0/15Qwen-Image-Edit 2511Alibaba · 20.4BQ4 GGUF16.0 GB1.7 minRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Animagine XL 4.0Cagliostro Lab · 2.6BFP168.9 GB4.2 sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Illustrious XL v0.1OnomaAI · 2.6BFP168.9 GB4.2 sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 27.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Playground v2.5Playground AI · 2.6BFP168.9 GB7.5 sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15PixArt-Σ XL 1024PixArt · 0.6BFP1612.8 GB1.5 sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15DreamShaper XL v2 TurboLykon · 2.6BFP168.9 GB1.3 sRuns well
74 ptsGreat (A) · 74 of 100 points: Model quality 26.1/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Pony Diffusion V6 XLPurpleSmartAI · 2.6BFP168.9 GB3.8 sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 25.6/45, Memory fit 25.0/25, Speed 13.4/15, Memory use 10.0/15AuraFlow v0.3fal · 6.9BFP810.4 GB13 sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 25.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Animagine XL 3.1Cagliostro Lab · 2.6BFP168.9 GB4.2 sRuns well
73 ptsGreat (A) · 73 of 100 points: Model quality 24.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15Stable Diffusion XL 1.0Stability AI · 2.6BFP168.9 GB4.5 sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.6/15SDXL-Lightning (4-step)ByteDance · 2.6BFP168.9 GB0.7 sRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 23.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.9/15Hunyuan-DiT v1.2Tencent · 1.5BFP169.3 GB6.0 sRuns well
68 ptsGood (B) · 68 of 100 points: Model quality 38.8/45, Memory fit 12.0/25, Speed 4.6/15, Memory use 12.8/15Qwen-ImageAlibaba · 20.4BFP813.3 GB1.8 minRuns well
65 ptsGood (B) · 65 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.3/15SDXL TurboStability AI · 2.6BFP167.6 GB0.2 sRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 21.6/45, Memory fit 20.0/25, Speed 15.0/15, Memory use 8.3/15Kandinsky 3Sber AI · 3.0BFP168.7 GB9.5 sRuns well
61 ptsGood (B) · 61 of 100 points: Model quality 18.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15Realistic Vision V5.1SG161222 · 0.9BFP162.8 GB1.2 sRuns well
60 ptsGood (B) · 60 of 100 points: Model quality 18.0/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15DreamShaper 8Lykon · 0.9BFP162.8 GB1.2 sRuns well
58 ptsGood (B) · 58 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15Stable Diffusion 1.5Stability AI / Runway · 0.9BFP162.8 GB1.2 sRuns well
56 ptsUsable (C) · 56 of 100 points: Model quality 13.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 2.7/15LCM DreamShaper v7Tsinghua (LCM) · 0.9BFP162.8 GB0.3 sRuns well
55 ptsUsable (C) · 55 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 3.2/15SD TurboStability AI · 0.9BFP163.3 GB0.1 sRuns well
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 0.0/15HunyuanImage 3.0 (80B-A13B)Tencent · 83.0BFP832.8 GB—Won't run

Video models on your NVIDIA GeForce RTX 4090

Grade · points Model Precision Memory Time per output Fit
78 ptsGreat (A) · 78 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 14.3/15CogVideoX 5B I2VZhipu AI · 5.6BFP814.9 GB2.7 minRuns well
78 ptsGreat (A) · 78 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.8/15CogVideoX 5BZhipu AI · 5.0BFP814.3 GB2.7 minRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 32.6/45, Memory fit 20.0/25, Speed 10.4/15, Memory use 15.0/15FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9BFP819.6 GB6.3 minRuns well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15LTX-Video 2BLightricks · 1.9BFP1617.5 GB25 sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 31.8/45, Memory fit 23.0/25, Speed 5.8/15, Memory use 15.0/15Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3BQ4 GGUF21.6 GB20.0 minTight fit
75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 13.2/15Wan 2.1 VACE 1.3BAlibaba · 2.2BFP813.7 GB3.9 minRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 24.3/45, Memory fit 25.0/25, Speed 13.7/15, Memory use 12.4/15Wan 2.1 T2V 1.3BAlibaba · 1.3BFP812.8 GB3.6 minRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 20.3/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15CogVideoX 2BZhipu AI · 1.7BFP1617.5 GB60 sRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 22.9/45, Memory fit 25.0/25, Speed 12.2/15, Memory use 15.0/15SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4BFP816.7 GB4.5 minRuns well
75 ptsGreat (A) · 75 of 100 points: Model quality 31.0/45, Memory fit 23.0/25, Speed 6.1/15, Memory use 15.0/15Wan 2.1 I2V 14B 480PAlibaba · 14.0BQ4 GGUF20.6 GB18.0 minTight fit
74 ptsGreat (A) · 74 of 100 points: Model quality 37.9/45, Memory fit 12.0/25, Speed 9.3/15, Memory use 15.0/15LTX-2.3Lightricks · 18.9BFP819.0 GB7.8 minRuns well
72 ptsGreat (A) · 72 of 100 points: Model quality 36.2/45, Memory fit 12.0/25, Speed 9.3/15, Memory use 15.0/15LTX-2 (19B, video + audio)Lightricks · 18.9BFP819.0 GB7.8 minRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 30.0/45, Memory fit 12.0/25, Speed 15.0/15, Memory use 15.0/15LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0BFP816.1 GB70 sRuns well
71 ptsGood (B) · 71 of 100 points: Model quality 25.6/45, Memory fit 18.0/25, Speed 13.1/15, Memory use 15.0/15Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0BFP822.0 GB3.9 minTight fit
67 ptsGood (B) · 67 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 4.7/15, Memory use 15.0/15Wan 2.2 I2V A14BAlibaba · 14.0BFP823.3 GB31.2 minTight fit
67 ptsGood (B) · 67 of 100 points: Model quality 37.9/45, Memory fit 10.0/25, Speed 4.7/15, Memory use 15.0/15Wan 2.2 T2V A14BAlibaba · 14.0BFP823.3 GB31.2 minTight fit
66 ptsGood (B) · 66 of 100 points: Model quality 27.3/45, Memory fit 18.0/25, Speed 6.2/15, Memory use 15.0/15Mochi 1 Preview (10B)Genmo · 10.0BFP821.9 GB17.3 minTight fit
65 ptsGood (B) · 65 of 100 points: Model quality 33.3/45, Memory fit 12.0/25, Speed 4.7/15, Memory use 15.0/15SkyReels V2 T2V 14B 540PSkywork · 14.0BFP1619.1 GB30.3 minRuns well
64 ptsGood (B) · 64 of 100 points: Model quality 30.9/45, Memory fit 10.0/25, Speed 8.2/15, Memory use 15.0/15Wan 2.2 TI2V 5BAlibaba · 5.0BFP822.1 GB10.1 minTight fit
63 ptsGood (B) · 63 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 4.2/15, Memory use 15.0/15Wan 2.1 I2V 14B 720PAlibaba · 14.0BFP823.3 GB39.0 minTight fit
63 ptsGood (B) · 63 of 100 points: Model quality 34.4/45, Memory fit 10.0/25, Speed 4.2/15, Memory use 15.0/15Wan 2.1 T2V 14BAlibaba · 14.0BFP823.3 GB39.0 minTight fit
61 ptsGood (B) · 61 of 100 points: Model quality 31.5/45, Memory fit 12.0/25, Speed 3.2/15, Memory use 15.0/15Open-Sora 2.0 (11B)HPC-AI Tech · 11.0BFP1619.3 GB65.0 minRuns well
61 ptsGood (B) · 61 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 3.7/15, Memory use 15.0/15Wan 2.2 Animate 14BAlibaba · 17.3BQ4 GGUF21.3 GB49.4 minTight fit
61 ptsGood (B) · 61 of 100 points: Model quality 32.6/45, Memory fit 10.0/25, Speed 3.4/15, Memory use 15.0/15Wan 2.1 VACE 14BAlibaba · 17.3BQ4 GGUF22.0 GB57.2 minTight fit
60 ptsGood (B) · 60 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 4.5/15AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3BFP164.7 GB20 sRuns well
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 0.0/15HunyuanVideo 1.5 (8.3B)Tencent · 8.3BFP823.9 GB—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 0.0/15SkyReels V2 T2V 14B 720PSkywork · 14.0BFP826.0 GB—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 0.0/15Step-Video T2V (30B)StepFun · 30.0BFP825.0 GB—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 0.0/15Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0BFP824.7 GB—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 0.0/15HunyuanVideo 13BTencent · 13.0BQ4 GGUF24.8 GB—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 0.0/15HunyuanVideo I2V 13BTencent · 13.0BQ4 GGUF24.8 GB—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 0.0/15Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0BFP1629.2 GB—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 0.0/15CogVideoX 1.5 5BZhipu AI · 5.6BFP831.2 GB—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 0.0/15Allegro (2.8B)Rhymes AI · 2.8BFP1624.7 GB—Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 405 of 536 LLMs run well on your NVIDIA GeForce RTX 4090.

Cheapest upgrade Intel Arc Pro B70 32.0 GB · $949 launch price +7 LLMs run well, including Llama 3.3 Nemotron Super 49B v1.5
Best value AMD Radeon PRO W7800 48GB 48.0 GB · $2,799 launch price +38 LLMs run well, including Qwen3 Coder Next (80B-A3B)
Biggest jump NVIDIA RTX PRO 6000 Blackwell 96.0 GB · $8,565 launch price +60 LLMs run well, including Qwen3.8 Flash Next (125B-A6B)

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.