What the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB) can run

We check your GPU or device against every model. Browsers can’t see how much memory you have, so confirm your exact model below.

Unified memory
48.0 GB
Usable for models
32.2 GB
Memory bandwidth
300 GB/s
FP16 compute
28.8 TFLOPS
490 / 619 LLMs run Best: Gemma 4 26B-A4B (A+) 59 / 60 Image models run Best: Krea 2 Turbo (A+) 41 / 43 Video models run Best: LTX-2.5 (22B, video + audio) (A) 68 / 70 Decision models run Best: Qwen3 Reranker 4B (A+)

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

LLMs on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Quality Model Quant Memory Speed Runs
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 26B-A4BGoogle · 26B (3.8B active)Q6_K24.7 GB54.1 tok/sRuns great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active)Q6_K32.1 GB65.1 tok/sRuns welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active)Q4_K_M24.8 GB86.9 tok/sRuns great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active)Q6_K31.8 GB65.1 tok/sRuns welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active)Q6_K26.8 GB48.9 tok/sRuns great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Sage-A1.5 35B-A3BInternScience · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)Q5_K_M25.8 GB74.8 tok/sRuns great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Flint (40B-A2.5B)Recursive · 40B (2.5B active)Q5_K_M31.7 GB85.3 tok/sRuns welltight fit
84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M25.3 GB86.9 tok/sRuns great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Agents-A1 35B-A3BInternScience · 35B (3.0B active)Q6_K32.1 GB65.1 tok/sRuns welltight fit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)Q6_K31.8 GB65.1 tok/sRuns welltight fit
82Great quality (A) · 82 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan Hy-Memory 30B-A3BTencent · 30B (3.0B active)Q5_K_M25.3 GB74.8 tok/sRuns great
81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)Q6_K31.9 GB65.1 tok/sRuns welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)Q5_K_M25.6 GB66.6 tok/sRuns great
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)Q5_K_M25.1 GB74.8 tok/sRuns great
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)Q6_K24.7 GB51.9 tok/sRuns great
92Excellent quality (A+) · 92 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.8 27BAlibaba · 28BQ5_K_M23.4 GB11.0 tok/sRuns well
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)Q5_K_M25.7 GB69.7 tok/sRuns great
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)Q5_K_M25.7 GB69.7 tok/sRuns great
91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.6 27BAlibaba · 28BQ5_K_M23.4 GB11.0 tok/sRuns well
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Nanbeige4.3 33BBOSS Zhipin (Nanbeige) · 33BQ4_K_M25.1 GB11.1 tok/sRuns well
74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)Q5_K_M25.6 GB66.6 tok/sRuns great
74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)Q5_K_M25.7 GB69.7 tok/sRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 27BAlibaba · 28BQ5_K_M23.4 GB11.0 tok/sRuns well
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)Q5_K_M26.0 GB69.7 tok/sRuns great
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 24B-A2BLiquid AI · 24B (2.5B active)Q6_K23.0 GB75.8 tok/sRuns great
89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Muse Glimmer 30BMeta · 30BQ5_K_M24.4 GB10.2 tok/sRuns well
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 30B-A3BAlibaba · 31B (3.3B active)Q5_K_M25.6 GB69.7 tok/sRuns great
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)Q5_K_M26.0 GB69.7 tok/sRuns great
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.TMax 27BAi2 · 27BQ5_K_M23.1 GB11.1 tok/sRuns well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 31BGoogle · 31BQ4_K_M23.9 GB11.8 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)Q8_026.8 GB50.5 tok/sRuns great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Maple Preview (20B-A1B)DeepGrove · 20B (1.5B active)Q8_024.7 GB85.1 tok/sRuns great
69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)Q5_K_M25.6 GB74.8 tok/sRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Fara 1.5 27BMicrosoft · 27BQ4_K_M20.4 GB13.5 tok/sRuns well
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Sarvam 30BSarvam AI · 32B (2.4B active)Q5_K_M26.2 GB87.8 tok/sRuns great
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.UI-Mate 27BTencent · 27BQ4_K_M20.4 GB13.5 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)Q4_K_M25.5 GB81.1 tok/sRuns great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)Q6_K24.8 GB65.1 tok/sRuns great
64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)Q8_026.9 GB50.5 tok/sRuns great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.Mellum2.1 Thinking (12B-A2.5B)JetBrains · 12B (2.5B active)Q8_016.2 GB58.3 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)Q3_K_M27.3 GB105 tok/sRuns great
77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.5 33BLG AI Research · 34BQ4_K_M24.9 GB10.7 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss 20BOpenAI · 21B (3.6B active)MXFP415.3 GB80.0 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)Q8_020.8 GB50.5 tok/sRuns great
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 12BGoogle · 12BQ4_K_M11.1 GB30.8 tok/sRuns great
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Axion 1.0 35BAxion · 35B (3.0B active)Q6_K32.1 GB65.1 tok/sRuns welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32BAlibaba · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.K2 Horizon 7BInstitute of Foundation Models · 9.0BQ4_K_M9.9 GB40.9 tok/sRuns great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 32B InstructAlibaba · 33BQ4_K_M25.7 GB11.0 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 30BIBM · 29BQ4_K_M23.2 GB12.6 tok/sRuns well
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Seed-OSS 36B InstructByteDance · 36BQ4_K_M27.4 GB10.2 tok/sRuns welltight fit
60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)F1619.2 GB51.5 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)Q4_K_M23.0 GB36.0 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Groot 19B A3B 261023GrootTeam · 19B (3.0B active)Q8_023.9 GB50.5 tok/sRuns great
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 2 (24B)Mistral AI · 24BQ4_K_M19.2 GB15.3 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3.1 32B ThinkAi2 · 32BQ4_K_M23.6 GB11.4 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.OpenReasoning Nemotron 32BNVIDIA · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Skywork OR1 32BSkywork · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 32BAlibaba · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4.3 36BNous Research · 36BQ4_K_M27.4 GB10.2 tok/sRuns welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Minibeipo-ai · 35B (3.0B active)Q6_K32.1 GB65.1 tok/sRuns welltight fit
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Bolt E4BNVIDIA · 8.0BQ8_011.8 GB41.7 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.LFM2 24B-A2BLiquid AI · 24B (2.3B active)Q6_K22.9 GB79.3 tok/sRuns great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.SenseNova Loop 9B PreviewSenseTime · 9.7BQ4_K_M9.5 GB38.1 tok/sRuns great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.6 Distill Qwen 9BXiaomi · 9.4BQ4_K_M9.2 GB39.1 tok/sRuns great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.EXAONE Deep 32BLG AI Research · 32BQ4_K_M24.8 GB11.5 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 32B 0414Zhipu AI · 33BQ4_K_M23.6 GB11.3 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.GLM-Z1 32B (0414)Zhipu AI · 33BQ4_K_M23.6 GB11.3 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 27B ITGoogle · 27BQ4_K_M20.7 GB13.4 tok/sRuns well
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 9BDeepReinforce · 9.7BQ4_K_M9.3 GB38.2 tok/sRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 30BIBM · 29BQ4_K_M22.9 GB12.8 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 E4BGoogle · 8.0BQ8_011.8 GB41.7 tok/sRuns great
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 9BAlibaba · 9.7BQ4_K_M9.3 GB38.2 tok/sRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.0 32BLG AI Research · 32BQ4_K_M23.4 GB11.5 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 1.2 (24B)Mistral AI · 24BQ4_K_M19.2 GB15.3 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3.1 32B InstructAi2 · 32BQ4_K_M23.6 GB11.4 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 32BDeepSeek · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.0 9BDeepReinforce · 9.7BQ4_K_M9.3 GB38.2 tok/sRuns great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 27B Text ITGoogle · 27BQ4_K_M20.5 GB13.6 tok/sRuns well
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)Q8_020.7 GB88.7 tok/sRuns great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.TMax 9BAi2 · 9.0BQ4_K_M8.9 GB41.1 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)Q4_K_M29.8 GB47.0 tok/sRuns welltight fit
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)F1620.2 GB46.0 tok/sRuns great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Baichuan M2 32BBaichuan · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.OpenHands LM 32BAll Hands AI · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 32B InstructAlibaba · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 1.1 (24B)Mistral AI · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 2507Mistral AI · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)Q8_020.1 GB60.2 tok/sRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning Plus (14B)Microsoft · 15BQ4_K_M13.8 GB25.1 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Terminal RSI 27BTeriminal-RSI · 28BQ4_K_M20.7 GB13.3 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Apriel 1.5 15B ThinkerServiceNow · 15BQ4_K_M13.8 GB24.8 tok/sRuns well
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active)Q8_020.8 GB50.5 tok/sRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Nanbeige4.2 3BBOSS Zhipin (Nanbeige) · 4.2BQ8_09.1 GB45.0 tok/sRuns great
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3.2 24BMistral AI · 24BQ4_K_M19.2 GB15.3 tok/sRuns well
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 38BShanghai AI Lab · 38BQ3_K_M24.1 GB12.4 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 2506Mistral AI · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 32B InstructAlibaba · 33BQ4_K_M25.7 GB11.0 tok/sRuns well
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Hemmingway 1.5Hemmingway · 27BQ4_K_M20.1 GB13.7 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning Vision 15BMicrosoft · 15BQ4_K_M14.1 GB24.4 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning (14B)Microsoft · 15BQ4_K_M13.8 GB25.1 tok/sRuns well
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 32B InstructAlibaba · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.SenseNova 6.8 Code2VideoSenseTime · 27BQ4_K_M20.4 GB13.5 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.UI-Mate 9BTencent · 9.4BQ4_K_M9.2 GB39.1 tok/sRuns great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.UI-Venus 2 9BAnt Group (inclusionAI) · 9.4BQ4_K_M9.2 GB39.1 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3.1 24BMistral AI · 24BQ4_K_M19.2 GB15.3 tok/sRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Labs Dory 1.0 4BNVIDIA · 4.0BQ8_07.9 GB47.1 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32B PreviewAlibaba · 33BQ4_K_M25.3 GB11.2 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 8BIBM · 8.8BQ4_K_M9.9 GB41.9 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 2505Mistral AI · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 14BAlibaba · 15BQ4_K_M13.5 GB24.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Reka Flash 3.1 (21B)Reka AI · 21BQ4_K_M17.0 GB17.6 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Spark-X2.6 4BSparkLLM · 4.1BQ8_07.8 GB45.6 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)Q8_020.3 GB50.5 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3 24B (2501)Mistral AI · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 27B ITGoogle · 27BQ4_K_M21.5 GB13.5 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 34B InstructTII · 34BQ4_K_M24.9 GB10.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Apriel Nemotron 15B ThinkerServiceNow · 15BQ4_K_M14.0 GB24.6 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.AceReason Nemotron 14BNVIDIA · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.OpenReasoning Nemotron 14BNVIDIA · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 14B InstructAlibaba · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 38BShanghai AI Lab · 38BQ3_K_M24.1 GB12.4 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4 14BNous Research · 15BQ4_K_M13.5 GB24.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 14B ReasoningMistral AI · 14BQ4_K_M13.0 GB26.4 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Voxtral Small 24BMistral AI · 24BQ4_K_M19.3 GB15.2 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Dolphin Mistral 24B Venice EditionCognitive Computations · 24BQ4_K_M19.2 GB15.3 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Codestral 22BMistral AI · 22BQ4_K_M18.6 GB16.6 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Command R (08-2024) 32BCohere · 32BQ4_K_M24.2 GB11.4 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 (14B)Microsoft · 15BQ4_K_M13.8 GB25.1 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 E2BGoogle · 5.1BQ8_08.7 GB81.5 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 14BShanghai AI Lab · 15BQ4_K_M14.0 GB24.4 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.DeepCoder 14B PreviewAgentica · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
62Good quality (B) · 62 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 4BAlibaba · 4.7BQ8_08.4 GB40.2 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 14BMistral AI · 14BQ4_K_M13.0 GB26.4 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2BQ5_K_M10.2 GB37.1 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 32B InstructAi2 · 32BQ4_K_M23.9 GB11.4 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL-Cowork 4.7BMicrosoft · 4.7BQ8_09.4 GB39.6 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 32BCohere · 32BQ4_K_M24.2 GB11.4 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24BQ4_K_M18.9 GB15.6 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Aya Vision 32BCohere · 33BQ4_K_M24.7 GB11.1 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 8B InstructAlibaba · 8.8BQ4_K_M9.7 GB42.0 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50BQ2_K25.8 GB12.1 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 8BShanghai AI Lab · 8.5BQ4_K_M9.6 GB43.2 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)Q3_K_M27.1 GB33.0 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Solar Pro Preview 22BUpstage · 22BQ4_K_M18.0 GB16.6 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 14BDeepSeek · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 14B InstructAlibaba · 15BQ4_K_M13.8 GB25.1 tok/sRuns well
61Good quality (B) · 61 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.TMax 4BAi2 · 4.2BQ8_07.9 GB44.5 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.JanusCoder 14BShanghai AI Lab · 15BQ4_K_M13.5 GB24.9 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Agents-A1 4BInternScience · 4.5BQ8_08.3 GB41.3 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 22B V2LLM4Binary · 22BQ4_K_M18.6 GB16.6 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 8BIBM · 8.8BQ4_K_M9.9 GB41.9 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.5 8BOpenBMB · 8.7BQ4_K_M9.7 GB42.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Mixtral 8x7B InstructMistral AI · 47B (12.9B active)Q3_K_M27.1 GB33.0 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)Q8_020.1 GB60.2 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 14B Instruct 1MAlibaba · 15BQ4_K_M13.8 GB24.9 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 8BAlibaba · 8.2BQ4_K_M9.4 GB45.0 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)F1617.1 GB62.7 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Fara 1.5 4BMicrosoft · 4.5BQ8_08.3 GB41.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)Q3_K_M28.6 GB35.2 tok/sRuns welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Nano 9B v2NVIDIA · 8.9BQ4_K_M8.7 GB41.4 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL 4.7BMicrosoft · 4.7BQ8_09.4 GB39.6 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.1V 9B ThinkingZhipu AI · 10BQ4_K_M9.8 GB35.8 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 12B ITGoogle · 12BQ4_K_M11.3 GB30.2 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.MiMo-VL 7B RLXiaomi · 8.3BQ4_K_M9.4 GB44.3 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Seed-Coder 8B ReasoningByteDance · 8.3BQ4_K_M9.3 GB44.6 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 2BOpenBMB · 2.5BQ8_06.2 GB74.4 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)F1620.0 GB46.0 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4B Thinking 2507Alibaba · 4.0BQ8_08.6 GB46.6 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.MiMo 7B RLXiaomi · 7.8BQ5_K_M9.9 GB38.9 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.GLM-Z1 9B (0414)Zhipu AI · 9.4BQ4_K_M9.2 GB39.2 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.EXAONE Deep 7.8BLG AI Research · 7.8BQ5_K_M9.8 GB38.9 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 22B (2409)Mistral AI · 22BQ4_K_M18.6 GB16.6 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)Q3_K_M31.8 GB30.6 tok/sRuns welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 8BMistral AI · 8.9BQ4_K_M9.8 GB41.3 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1R 7BTII · 7.6BQ5_K_M8.9 GB40.1 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 4B InstructAlibaba · 4.4BQ8_09.1 GB42.2 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 8BShanghai AI Lab · 7.9BQ5_K_M9.3 GB38.3 tok/sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3 7B ThinkAi2 · 7.3BQ5_K_M9.8 GB41.7 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Seed-Coder 8B InstructByteDance · 8.3BQ4_K_M9.3 GB44.6 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4B Instruct 2507Alibaba · 4.0BQ8_08.6 GB46.6 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 7B InstructAlibaba · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.OpenReasoning Nemotron 7BNVIDIA · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.LFM3 1.7BLiquid AI · 1.7BF166.7 GB49.9 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 7B InstructTencent · 7.5BQ5_K_M9.6 GB40.6 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Foundation-Sec 8B ReasoningCisco Foundation AI · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B InstructAlibaba · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Qianfan-OCR 4BBaidu · 4.7BQ8_09.4 GB39.6 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 10B InstructTII · 10BQ4_K_M10.8 GB35.7 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM4 8BOpenBMB · 8.2BQ4_K_M8.4 GB45.0 tok/sRuns great
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Bolt 74B-A9BNVIDIA · 75B (9.0B active)Q2_K33.2 GB47.2 tok/sRuns wellover GPU memory limit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 34B Chat01.AI · 34BQ4_K_M25.2 GB10.7 tok/sRuns well
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E4BGoogle · 7.9BQ8_011.6 GB46.9 tok/sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 3BIBM · 3.7BQ8_07.7 GB51.2 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3 7B InstructAi2 · 7.3BQ5_K_M9.8 GB41.7 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Mistral Nemo 12B InstructMistral AI · 12BQ4_K_M12.0 GB30.2 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 9B ITGoogle · 9.2BQ4_K_M10.4 GB39.9 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 20B ChatShanghai AI Lab · 20BQ4_K_M16.9 GB18.5 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 9B 0414Zhipu AI · 9.4BQ4_K_M9.2 GB39.2 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4BAlibaba · 4.0BQ8_08.6 GB46.6 tok/sRuns great
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Kolibri 1 (78B-A3.5B)Aleph Alpha · 78B (3.5B active)Q2_K34.6 GB96.1 tok/sRuns wellover GPU memory limit
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Nanobeipo-ai · 9.4BQ4_K_M9.2 GB39.1 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-o 2.6 8BOpenBMB · 8.7BQ4_K_M8.9 GB42.5 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Llama 8BDeepSeek · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Foundation-Sec 1.1 8B InstructCisco Foundation AI · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.InternVL2.5 8BShanghai AI Lab · 8.1BQ5_K_M10.0 GB37.7 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 7B InstructAlibaba · 8.3BQ4_K_M8.7 GB44.4 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B Instruct 1MAlibaba · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 7B InstructTII · 7.6BQ5_K_M8.9 GB40.1 tok/sRuns great
45Fair quality (C) · 45 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Command R 35B (v01)Cohere · 35BQ3_K_M31.1 GB13.6 tok/sRuns welltight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 9BFastino · 7.9BQ5_K_M9.1 GB38.3 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Pixtral 12B (2409)Mistral AI · 12BQ4_K_M12.1 GB29.7 tok/sRuns well
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Nano 4BNVIDIA · 4.0BQ8_07.5 GB47.2 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.InternLM3 8B InstructShanghai AI Lab · 8.8BQ4_K_M8.9 GB41.8 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 (Llama 3.1 8B)Nous Research · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 8B InstructMeta · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Fara 7BMicrosoft · 8.3BQ4_K_M8.7 GB44.4 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.LFM3-VL 2BLiquid AI · 1.9BF167.1 GB45.0 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.LightOnOCR-3 4BLightOn · 4.5BQ8_08.3 GB41.3 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Unlimited OCR 2 (3B-A0.6B)Baidu · 3.3B (0.6B active)F1610.4 GB88.3 tok/sRuns great
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 9B Chat 1MZhipu AI · 9.5BQ4_K_M9.6 GB38.8 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active)Q2_K35.2 GB105 tok/sRuns wellover GPU memory limit
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 9B Chat (2024)Zhipu AI · 9.4BQ4_K_M9.2 GB39.2 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Chandra OCR 2Datalab · 5.3BQ6_K7.8 GB48.2 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Ministral 8B (2410)Mistral AI · 8.0BQ5_K_M10.1 GB37.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 7.8BLG AI Research · 7.8BQ5_K_M9.8 GB38.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 7B InstructTII · 7.5BQ5_K_M9.4 GB40.8 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Tülu 3 8BAi2 · 8.0BQ5_K_M9.9 GB37.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 32B ChatAlibaba · 33BQ4_K_M25.2 GB11.3 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 13B InstructAi2 · 14BQ4_K_M14.9 GB26.8 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)Q8_021.5 GB53.4 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 33B InstructDeepSeek · 33BQ4_K_M25.6 GB11.0 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 2.6 8BOpenBMB · 8.1BQ4_K_M8.6 GB45.5 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8BQ8_08.3 GB48.8 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Aya 23 35BCohere · 35BQ3_K_M31.1 GB13.6 tok/sRuns welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Apertus v1.5 8BSwiss AI · 8.9BQ4_K_M9.7 GB41.4 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 34BLLaVA · 35BQ4_K_M25.4 GB10.6 tok/sRuns well
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 8B InstructIBM · 8.2BQ4_K_M9.5 GB45.1 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 8BIBM · 8.2BQ4_K_M9.5 GB45.1 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium 128K InstructMicrosoft · 14BQ4_K_M13.4 GB26.4 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E2BGoogle · 5.4BF1614.2 GB43.2 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5BQ8_09.0 GB41.6 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Prover V2 7BDeepSeek · 6.9BQ5_K_M12.1 GB44.0 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.CodeGeeX4 All 9BZhipu AI · 9.4BQ4_K_M9.2 GB39.2 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 3BIBM · 3.4BQ8_07.4 GB55.1 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.WeVisOne-VL 4BTencent · 4.8BQ6_K8.3 GB52.9 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Small 8K InstructMicrosoft · 7.4BQ5_K_M9.5 GB41.2 tok/sRuns great
45Fair quality (C) · 45 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 4B ITGoogle · 4.3BQ8_08.0 GB43.6 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Multimodal InstructMicrosoft · 5.6BQ6_K8.8 GB45.9 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Omni 7BAlibaba · 11BQ4_K_M10.2 GB34.3 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium (14B)Microsoft · 14BQ4_K_M12.5 GB26.4 tok/sRuns well
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini (3.8B)Microsoft · 3.8BQ8_08.3 GB48.8 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 7B InstructAlibaba · 7.6BQ5_K_M9.1 GB39.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 3BMistral AI · 3.9BQ8_08.1 GB48.7 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 8B InstructIBM · 8.2BQ4_K_M9.5 GB45.1 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 4B ITGoogle · 4.3BQ8_08.0 GB43.6 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 Mini InstructMicrosoft · 3.8BQ8_010.4 GB49.1 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.CogVLM2 Llama 3 Chat 19BZhipu AI · 20BQ4_K_M19.4 GB18.9 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)F1610.4 GB88.3 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.InternVL2 8BShanghai AI Lab · 8.1BQ4_K_M9.2 GB45.6 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Llama 3 8BNous Research · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.6 8BOpenChat · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Chat 20BShanghai AI Lab · 20BQ4_K_M16.9 GB18.5 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 4B InstructTencent · 4.2BQ8_08.9 GB44.4 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Aya Vision 8BCohere · 8.6BQ4_K_M8.8 GB42.7 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)Q8_020.0 GB54.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 7B InstructAlibaba · 8.3BQ4_K_M8.7 GB44.4 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 34B InstructIBM · 34BQ4_K_M24.1 GB10.9 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 14B ChatAlibaba · 14BQ4_K_M18.5 GB26.0 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4BQ4_K_M9.6 GB43.8 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Command R7BCohere · 8.0BQ4_K_M8.4 GB45.9 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Yi 34B Chat01.AI · 34BQ4_K_M25.2 GB10.7 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 Vision InstructMicrosoft · 4.2BQ8_010.8 GB45.2 tok/sRuns great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 11B Vision InstructMeta · 11BQ4_K_M11.0 GB34.5 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.North Micro VisionCohere · 2.5BQ8_06.7 GB75.6 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5-VL 3BLiquid AI · 3.1BQ8_06.6 GB60.1 tok/sRuns great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Llama 3 8B InstructMeta · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Jamba Reasoning 3BAI21 Labs · 3.2BQ8_06.6 GB58.6 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 20BShanghai AI Lab · 20BQ4_K_M16.9 GB18.5 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 7B ChatShanghai AI Lab · 7.7BQ5_K_M9.7 GB39.3 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)F1617.5 GB51.5 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 2.6BLiquid AI · 2.7BQ8_06.2 GB69.4 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.AFM 4.5BArcee AI · 4.6BQ8_08.7 GB40.6 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 34B InstructMeta · 34BQ4_K_M25.4 GB10.9 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Command R7B ArabicCohere · 8.0BQ4_K_M8.4 GB45.9 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.SmolLM3 3BHugging Face · 3.1BQ8_07.0 GB60.9 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 9B Chat01.AI · 8.8BQ4_K_M9.4 GB41.7 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 128K InstructMicrosoft · 3.8BQ8_010.4 GB49.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Apertus 8B InstructSwiss AI · 8.1BQ4_K_M9.2 GB45.7 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 8BCohere · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 6.7B InstructDeepSeek · 6.7BQ5_K_M12.3 GB45.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 SOLAR 10.7BNous Research · 11BQ4_K_M10.5 GB34.3 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.SOLAR 10.7B InstructUpstage · 11BQ4_K_M10.5 GB34.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Jamba2 3BAI21 Labs · 3.0BQ8_06.4 GB61.9 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 8B InstructIBM · 8.2BQ4_K_M8.8 GB45.1 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 Micro (3B)IBM · 3.4BQ8_07.4 GB55.1 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.3Mistral AI · 7.3BQ5_K_M9.4 GB42.0 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 7B InstructAi2 · 7.3BQ5_K_M10.5 GB41.7 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 7BGoogle · 8.5BQ4_K_M12.1 GB43.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 15B InstructBigCode · 16BQ4_K_M13.6 GB23.1 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 7B InstructZyphra · 7.4BQ5_K_M9.2 GB41.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-OCR 1.0 1.3BOpenBMB · 1.3BF165.9 GB66.5 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.TMax 2BAi2 · 1.9BF167.0 GB46.0 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Vision 128K InstructMicrosoft · 4.2BQ8_010.8 GB45.2 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.0 7.8B InstructLG AI Research · 7.8BQ5_K_M9.3 GB38.9 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.TeleOCRXingChen-AGI · 1.4BF167.0 GB60.8 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 9B V2LLM4Binary · 8.8BQ4_K_M9.4 GB41.7 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 6.7B V2LLM4Binary · 6.7BQ5_K_M12.3 GB45.1 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Voxtral Mini 3BMistral AI · 4.7BQ8_09.1 GB40.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM3 4BOpenBMB · 4.1BQ8_07.8 GB46.1 tok/sRuns great
37Basic quality (D) · 37 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.S5 nanoMaritaca AI · 4.7BQ8_08.4 GB40.2 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.PaddleOCR-VL 1.6 0.9BBaidu · 1.0BF165.2 GB90.0 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Falcon3 Mamba 7B InstructTII · 7.3BQ5_K_M8.4 GB41.8 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.7 1BOpenBMB · 1.6BF166.4 GB55.7 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 4K InstructMicrosoft · 3.8BQ8_08.8 GB49.1 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Mistral 7BNous Research · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B BetaNexusflow · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 13B InstructMeta · 13BQ3_K_M16.3 GB36.6 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 2B InstructAlibaba · 2.1BF168.4 GB40.6 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 2BAlibaba · 2.3BQ8_05.7 GB82.6 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 7B InstructAlibaba · 7.6BQ5_K_M8.8 GB39.9 tok/sRuns great
33Basic quality (D) · 33 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (0106)OpenChat · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.SQLCoder 7B v2Defog · 6.7BQ5_K_M12.3 GB45.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H MicroIBM · 3.2BQ8_06.6 GB58.8 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 9B Chat01.AI · 8.8BQ4_K_M9.0 GB41.7 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 20B InstructIBM · 20BQ4_K_M15.6 GB18.3 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Codestral Mamba 7BMistral AI · 7.3BQ5_K_M8.4 GB41.7 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Mathstral 7BMistral AI · 7.3BQ5_K_M9.4 GB42.0 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.2Mistral AI · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mistral 7B DPONous Research · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (1210)OpenChat · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
35Basic quality (D) · 35 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 3B InstructMeta · 3.2BQ8_07.5 GB58.4 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Aya 23 8BCohere · 8.0BQ4_K_M9.1 GB45.9 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)Q2_K35.9 GB105 tok/sSlowfar over GPU memory limit
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 3B InstructTII · 3.2BQ8_06.8 GB59.5 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 3B InstructAlibaba · 3.1BQ8_06.8 GB60.7 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 7BShanghai AI Lab · 7.7BQ5_K_M9.7 GB39.3 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.RecurrentGemma 9B ITGoogle · 9.6BQ4_K_M9.2 GB38.2 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.OpenHermes 2.5 Mistral 7BTeknium · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B AlphaBerkeley · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Gemma 1.1 7B ITGoogle · 8.5BQ4_K_M12.1 GB43.1 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 3B InstructAlibaba · 3.8BQ8_07.4 GB50.0 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 7B ChatAlibaba · 7.7BQ5_K_M12.9 GB39.4 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active)Q2_K35.9 GB105 tok/sSlowfar over GPU memory limit
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 8B Instruct (128K)IBM · 8.1BQ4_K_M9.3 GB45.7 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 1BOpenBMB · 1.1BF165.5 GB80.0 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 3B InstructAlibaba · 3.1BQ8_06.8 GB60.7 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 70B InstructMeta · 69BQ2_K32.1 GB8.8 tok/sSlowtight fit
29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.1Mistral AI · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Gemma 7B ITGoogle · 8.5BQ4_K_M12.1 GB43.1 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 15B (base)BigCode · 16BQ4_K_M13.6 GB23.1 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 Llama 3.2 3BNous Research · 3.2BQ8_07.5 GB58.4 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.LFM2 2.6BLiquid AI · 2.6BQ8_06.0 GB72.9 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 1.7BAlibaba · 2.0BF168.2 GB42.6 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 7B InstructMeta · 6.7BQ5_K_M12.3 GB45.1 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 13BMicrosoft · 13BQ3_K_M12.9 GB36.6 tok/sRuns great
27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 Mistral 7BLLaVA · 7.6BQ5_K_M9.6 GB40.2 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Omni 3BAlibaba · 5.5BQ6_K8.0 GB46.1 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Falcon Mamba 7B InstructTII · 7.3BQ5_K_M8.4 GB41.8 tok/sRuns great
27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Neural Chat 7B v3.3Intel · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 3B InstructTII · 3.2BQ8_07.3 GB58.0 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek LLM 67B ChatDeepSeek · 67BQ2_K31.7 GB9.0 tok/sSlowtight fit
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 6B Chat01.AI · 6.1BQ6_K8.4 GB42.2 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 13B ChatMeta · 13BQ3_K_M12.9 GB36.6 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 1.2B InstructLiquid AI · 1.2BF165.6 GB73.8 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Baichuan 2 13B ChatBaichuan · 14BQ3_K_M13.3 GB34.3 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 2B InstructIBM · 2.5BQ8_06.5 GB74.1 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 2BIBM · 2.5BQ8_06.5 GB74.1 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.WizardMath 7B v1.1WizardLM · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Zephyr 7B BetaHugging Face · 7.2BQ5_K_M9.4 GB42.0 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 2.4BLG AI Research · 2.4BQ8_06.4 GB77.8 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.0 1.2BLG AI Research · 1.3BF166.2 GB67.5 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 12B ChatStability AI · 12BQ3_K_M10.0 GB39.2 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 70B ChatMeta · 69BQ2_K32.1 GB8.8 tok/sSlowtight fit
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 2B InstructIBM · 2.5BQ8_06.5 GB74.1 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 2BGoogle · 2.6BQ8_06.4 GB71.8 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H 1BIBM · 1.5BF166.2 GB59.2 tok/sRuns great
27Basic quality (D) · 27 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.WeVisOne VL 2BTencent · 2.4BQ8_06.7 GB76.8 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.WizardLM 13B v1.2WizardLM · 13BQ3_K_M12.9 GB36.6 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 13BLLaVA · 13BQ3_K_M13.1 GB35.7 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 7BMicrosoft · 6.7BQ5_K_M10.1 GB45.1 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 7BBigCode · 7.2BQ5_K_M8.8 GB42.4 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Granite Vision 3.2 2BIBM · 3.0BQ8_07.0 GB62.9 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.DeepScaleR 1.5B PreviewAgentica · 1.8BF167.0 GB48.5 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Kimi Dev 72BMoonshot AI · 73BQ2_K34.9 GB7.1 tok/sSlowover GPU memory limit
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)F1610.3 GB73.3 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Baichuan 2 7B ChatBaichuan · 7.5BQ5_K_M10.7 GB40.5 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 1.5B InstructAlibaba · 1.5BF166.5 GB56.1 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 1.5B InstructTII · 1.6BF166.5 GB55.7 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)Q2_K36.4 GB34.5 tok/sSlowfar over GPU memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 2B InstructIBM · 2.6BQ8_06.3 GB71.3 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Vicuna 13B v1.5LMSYS · 13BQ3_K_M12.9 GB36.6 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 7B ChatMeta · 6.7BQ5_K_M10.1 GB45.1 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM2 2.2B InstructHugging Face · 2.3BQ8_07.2 GB83.3 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 3B Instruct (128K)IBM · 3.5BQ8_09.5 GB53.9 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Mini 4B InstructNVIDIA · 4.2BQ8_08.2 GB44.7 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.LFM2 1.2BLiquid AI · 1.2BF165.6 GB73.8 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 1.5B InstructAlibaba · 1.5BF166.5 GB56.1 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 1.6BLiquid AI · 1.6BF166.4 GB54.7 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)F1610.2 GB73.3 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Stable Code Instruct 3BStability AI · 2.8BQ8_08.8 GB67.0 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 0.8BAlibaba · 0.9BF165.0 GB99.3 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 1.8B InstructTencent · 1.8BF167.3 GB48.3 tok/sRuns great
17Basic quality (D) · 17 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek LLM 7B ChatDeepSeek · 6.9BQ5_K_M10.1 GB44.0 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 2.2B InstructHugging Face · 2.3BQ8_07.2 GB83.3 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Yi 6B Chat01.AI · 6.1BQ6_K8.4 GB42.2 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 2B InstructAlibaba · 2.2BQ8_05.8 GB84.8 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8BF167.0 GB48.5 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 1.7B InstructHugging Face · 1.7BF168.2 GB50.5 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.StarCoder 15BBigCode · 16BQ2_K9.7 GB38.2 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4 70BNous Research · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.3 70B InstructMeta · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
21Basic quality (D) · 21 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.d1 2BLiquid AI · 1.9BF167.1 GB45.0 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 2.7B InstructZyphra · 2.7BQ8_06.4 GB70.5 tok/sRuns great
15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 7BLLaVA · 7.1BQ5_K_M10.3 GB43.1 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 72B InstructAlibaba · 73BQ2_K34.9 GB7.1 tok/sSlowover GPU memory limit
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 72B InstructAlibaba · 73BQ2_K35.2 GB7.0 tok/sSlowover GPU memory limit
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 1B InstructMeta · 1.2BF165.9 GB69.7 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Llama 70BDeepSeek · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Tülu 3 70BAi2 · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 1.8B ChatShanghai AI Lab · 1.9BF167.8 GB45.7 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 1.5B InstructAlibaba · 1.5BF166.4 GB56.1 tok/sRuns great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Falcon 40B InstructTII · 42BQ2_K20.1 GB14.5 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 70B InstructMeta · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Vicuna 7B v1.5LMSYS · 6.7BQ5_K_M10.1 GB45.1 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 3BBigCode · 3.0BQ8_06.6 GB61.9 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 (Llama 3.1 70B)Nous Research · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 1.5B Chat01.AI · 1.5BF167.7 GB58.4 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 1BGoogle · 1.0BF165.2 GB86.4 tok/sRuns great
17Basic quality (D) · 17 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 2BFastino · 1.9BF167.0 GB46.0 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.QVQ 72B PreviewAlibaba · 73BQ2_K35.2 GB7.0 tok/sSlowover GPU memory limit
13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.OLMo 7B InstructAi2 · 6.9BQ5_K_M9.1 GB44.2 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.StableLM Zephyr 3BStability AI · 2.8BQ8_07.5 GB67.0 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 1B InstructTII · 1.7BF167.1 GB51.7 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron 70B InstructNVIDIA · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Apertus v1.5 70BSwiss AI · 72BQ2_K34.7 GB7.1 tok/sSlowover GPU memory limit
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Phi-2 2.7BMicrosoft · 2.8BQ8_06.8 GB67.4 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Spark X2.6 1.7BSparkLLM · 1.7BF166.7 GB50.5 tok/sRuns great
11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.InternLM 7BShanghai AI Lab · 7.3BQ5_K_M9.4 GB41.6 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 1.5B InstructAlibaba · 1.5BF166.5 GB56.1 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.LFM2 700MLiquid AI · 0.7BF164.8 GB117 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 72B InstructAlibaba · 73BQ2_K34.9 GB7.1 tok/sSlowover GPU memory limit
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 72B InstructAlibaba · 73BQ2_K35.2 GB7.0 tok/sSlowover GPU memory limit
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 1.7B InstructHugging Face · 1.7BF167.0 GB50.5 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 1B InstructAi2 · 1.5BF166.7 GB58.4 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 1.3B InstructDeepSeek · 1.4BF167.5 GB64.0 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 1.3B V2LLM4Binary · 1.4BF167.5 GB64.0 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 2BGoogle · 2.5BQ8_06.0 GB74.7 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 0.6BAlibaba · 0.8BF165.6 GB115 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Apertus 70B InstructSwiss AI · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
15Basic quality (D) · 15 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.surya ocr 2.5Datalab · 0.7BF164.7 GB125 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 1.6B ChatStability AI · 1.6BF167.3 GB52.7 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 Zephyr 1.6BStability AI · 1.6BF167.3 GB52.7 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2B ITGoogle · 2.5BQ8_06.0 GB74.7 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Llama 3 70B InstructMeta · 71BQ2_K34.1 GB7.3 tok/sSlowover GPU memory limit
40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 72B InstructAlibaba · 73BQ2_K33.6 GB7.1 tok/sSlowover GPU memory limit
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 0.5B InstructTII · 0.5BF164.4 GB166 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 350MLiquid AI · 0.4BF164.0 GB247 tok/sRuns great
5Basic quality (D) · 5 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Falcon 7B InstructTII · 7.2BQ5_K_M8.3 GB42.1 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 450MLiquid AI · 0.5BF164.2 GB192 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 78BShanghai AI Lab · 78BQ2_K37.2 GB6.6 tok/sSlowfar over GPU memory limit
11Basic quality (D) · 11 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 0.8BFastino · 0.8BF164.8 GB115 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.LFM2 350MLiquid AI · 0.4BF164.0 GB247 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H 350MIBM · 0.3BF163.9 GB254 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 500M InstructHugging Face · 0.5BF164.5 GB169 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 0.5B InstructAlibaba · 0.5BF164.3 GB176 tok/sRuns great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 0.5B InstructTencent · 0.5BF165.1 GB160 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 230MLiquid AI · 0.2BF163.7 GB376 tok/sRuns great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 0.5B InstructAlibaba · 0.5BF164.3 GB176 tok/sRuns great
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 360M InstructHugging Face · 0.4BF164.2 GB240 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.TinyLlama 1.1B ChatTinyLlama · 1.1BF165.4 GB78.5 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 0.5B InstructAlibaba · 0.5BF164.3 GB176 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.ERNIE 4.5 0.3BBaidu · 0.4BF164.0 GB240 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 256M InstructHugging Face · 0.3BF163.9 GB332 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 270MGoogle · 0.3BF163.7 GB320 tok/sRuns great
5Basic quality (D) · 5 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 360M InstructHugging Face · 0.4BF164.0 GB240 tok/sRuns great
4Basic quality (D) · 4 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 135M InstructHugging Face · 0.1BF163.6 GB665 tok/sRuns great
3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 Tiny 90M InstructTII · 0.1BF163.5 GB960 tok/sRuns great
2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 135M InstructHugging Face · 0.1BF163.5 GB665 tok/sRuns great
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss 120BOpenAI · 117B (5.1B active)MXFP470.1 GB—Won't run
69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Kimi K3.1 Pro (2.8T)Moonshot AI · 2,780B (104.0B active)Q2_K1,115 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4.1 Flash 1017 (552B-A16B)DeepSeek · 763B (16.0B active)Q2_K308 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K305 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.8 Max (2.4T-A95B)Alibaba · 2,446B (95.0B active)Q2_K982 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Kimi K3 (2.8T)Moonshot AI · 2,780B (104.0B active)Q2_K1,115 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.6 Pro (1T-A42B)Xiaomi · 1,024B (42.0B active)Q2_K413 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.1 Flash 1019 (560B-A25B)Ant Group (inclusionAI) · 572B (25.0B active)Q2_K232 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M3.1 Flash (428B-A23B)MiniMax · 429B (23.0B active)Q2_K176 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Step 5 Preview (600B-A27B)StepFun · 604B (27.0B active)Q2_K245 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.GLM-5.3 Flash (320B-A18B)Zhipu AI · 321B (18.0B active)Q2_K132 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active)Q2_K128 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4.1 Flash (552B-A16B)DeepSeek · 763B (16.0B active)Q2_K308 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 4 (1T-A52B)Mistral AI · 1,053B (52.0B active)Q2_K425 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.8 Flash Next (125B-A6B)Alibaba · 180B (6.0B active)Q2_K75.4 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K305 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan Hy4 Preview (780B)Tencent · 780B (55.0B active)Q2_K316 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Muse Spark Open (816B-A42B)Meta · 822B (42.0B active)Q2_K333 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4 Pro (1.6T-A49B)DeepSeek · 1,651B (49.0B active)Q2_K664 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2.6 (1T)Moonshot AI · 1,027B (32.0B active)Q2_K415 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.1 Flash (560B-A25B)Ant Group (inclusionAI) · 572B (25.0B active)Q2_K232 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.5 Pro (1T-A42B)Xiaomi · 1,023B (42.0B active)Q2_K413 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Intern-S2 (397B-A17B)Shanghai AI Lab · 403B (17.0B active)Q2_K165 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.GLM-5.1 (744B-A40B)Zhipu AI · 754B (40.0B active)Q2_K305 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nex N2 Pro (397B-A17B)Nex-AGI · 397B (17.0B active)Q2_K162 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4 Pro (April 2026)DeepSeek · 1,599B (49.0B active)Q2_K643 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Naive N0.5 Flash (309B-A15.5B)Naive AI · 309B (15.5B active)Q2_K127 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 397B-A17BAlibaba · 403B (17.0B active)Q2_K165 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M3 (427B)MiniMax · 427B (25.0B active)Q2_K175 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.GLM-5 (744B-A40B)Zhipu AI · 754B (40.0B active)Q2_K305 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.K2-Horizon (375B-A23B)Institute of Foundation Models · 379B (23.0B active)Q2_K157 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan Hy3 (295B-A21B)Tencent · 299B (21.0B active)Q2_K125 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Beam 1.0 (501B-A23B)Reflection AI · 501B (23.4B active)Q2_K204 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2.5 (1T)Moonshot AI · 1,027B (32.0B active)Q2_K415 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active)Q2_K415 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4 Flash (284B-A13B)DeepSeek · 304B (13.0B active)Q2_K125 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.5 (310B-A15B)Xiaomi · 311B (15.0B active)Q2_K128 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 397B-A17BDeepReinforce · 403B (17.0B active)Q2_K165 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Super VL 120B-A12BNVIDIA · 124B (12.0B active)Q2_K53.0 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3.2 (671B)DeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Inkling Small (276B-A12B)Thinking Machines Lab · 266B (12.0B active)Q2_K110 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.7 (355B-A32B)Zhipu AI · 358B (32.0B active)Q2_K150 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Inkling (975B-A41B)Thinking Machines Lab · 952B (41.0B active)Q2_K384 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M2.7 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K96.7 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Step 3.7 Flash (198B-A11B)StepFun · 201B (11.0B active)Q2_K84.2 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Ultra 550B-A55BNVIDIA · 561B (55.0B active)Q2_K227 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 0528 (671B)DeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2 Thinking (1T)Moonshot AI · 1,026B (32.0B active)Q2_K414 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 122B-A10BDeepReinforce · 125B (10.0B active)Q2_K53.4 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3.2 ExpDeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Ling 2.6 1TAnt Group (inclusionAI) · 1,025B (63.0B active)Q2_K413 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M2.5 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K96.7 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 (671B)DeepSeek · 671B (37.0B active)Q2_K272 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V4 Flash (April 2026)DeepSeek · 291B (13.0B active)Q2_K120 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)Q2_K53.4 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Step 3.5 Flash (196B-A11B)StepFun · 199B (11.0B active)Q2_K83.4 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3.1 TerminusDeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3.1 (671B)DeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2 Instruct 0905 (1T)Moonshot AI · 1,026B (32.0B active)Q2_K414 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M2.1 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K96.7 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active)Q2_K98.8 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active)Q2_K197 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2 Flash (309B-A15B)Xiaomi · 310B (15.0B active)Q2_K127 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active)Q2_K406 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 3 (675B)Mistral AI · 675B (41.0B active)Q2_K274 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active)Q2_K98.8 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Solar Open 2 250BUpstage · 250B (15.0B active)Q2_K105 GB—Won't run
62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active)Q2_K414 GB—Won't run
62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.MiniMax M2 (230B-A10B)MiniMax · 229B (10.0B active)Q2_K96.7 GB—Won't run
62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 235B-A22B InstructAlibaba · 236B (22.0B active)Q2_K99.0 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Command A+ (218B-A25B)Cohere · 219B (25.0B active)Q2_K90.9 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active)Q2_K98.4 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.LongCat Flash Chat (560B)Meituan · 562B (27.0B active)Q2_K228 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active)Q2_K52.7 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 235B-A22BAlibaba · 235B (22.0B active)Q2_K98.7 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Devstral 2 (123B)Mistral AI · 125BQ2_K56.1 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active)Q2_K101 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active)Q2_K51.8 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Ultra 253B v1NVIDIA · 253BQ2_K109 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Baichuan M3 235B-A22BBaichuan · 235B (22.0B active)Q2_K98.8 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.6 (355B-A32B)Zhipu AI · 357B (32.0B active)Q2_K149 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3 0324 (671B)DeepSeek · 685B (37.0B active)Q2_K278 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.6VZhipu AI · 108B (12.0B active)Q2_K47.8 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.MiniMax-M1 80KMiniMax · 456B (45.9B active)Q2_K186 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Command A Reasoning (111B)Cohere · 111BQ2_K48.3 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5 (355B-A32B)Zhipu AI · 358B (32.0B active)Q2_K150 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active)Q2_K54.6 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.MiniMax-M1 40KMiniMax · 456B (45.9B active)Q2_K186 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active)Q2_K51.1 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Medium 3.5 (128B)Mistral AI · 128BQ2_K57.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Trinity Large Thinking (400B-A13B)Arcee AI · 399B (13.0B active)Q2_K163 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Command A (111B)Cohere · 111BQ2_K48.3 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active)Q2_K125 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5VZhipu AI · 108B (12.0B active)Q2_K47.8 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4 405BNous Research · 406BQ2_K170 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling 2.6 Flash (104B-A7.4B)Ant Group (inclusionAI) · 107B (7.4B active)Q2_K46.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 2.1 (2411)Mistral AI · 123BQ2_K55.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Solar Open 100BUpstage · 103B (12.0B active)Q2_K45.8 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)Q2_K48.9 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 2 (123B)Mistral AI · 123BQ2_K55.3 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Probeipo-ai · 397B (17.0B active)Q2_K162 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Pixtral Large 124B (2411)Mistral AI · 124BQ2_K55.7 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K44.9 GB—Won't run
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.dots.llm1 Instructrednote · 143B (14.0B active)Q2_K68.6 GB—Won't run
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K44.9 GB—Won't run
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.MiniMax-Text-01MiniMax · 456B (45.9B active)Q2_K186 GB—Won't run
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Tülu 3 405BAi2 · 406BQ2_K170 GB—Won't run
52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3 (671B)DeepSeek · 671B (37.0B active)Q2_K272 GB—Won't run
52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Sarvam 105BSarvam AI · 106B (10.0B active)Q2_K45.9 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 (236B)DeepSeek · 236B (21.0B active)Q2_K98.0 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Leanstral 119B-A6BMistral AI · 119B (6.5B active)Q2_K51.1 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active)Q2_K98.0 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2.5 1210DeepSeek · 236B (21.0B active)Q2_K98.0 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 405B InstructMeta · 406BQ2_K170 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 4 Maverick (17B x 128E)Meta · 402B (17.0B active)Q2_K165 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 4 Scout 17B-16EMeta · 109B (17.0B active)Q2_K48.2 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Command R+ (08-2024) 104BCohere · 104BQ2_K46.8 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2.5DeepSeek · 236B (21.0B active)Q2_K98.0 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Groot 65B A6B 261023GrootTeam · 118B (6.0B active)Q2_K50.7 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Jamba 1.5 LargeAI21 Labs · 399B (94.0B active)Q2_K163 GB—Won't run
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 flash SanteAnt Group (inclusionAI) · 127B (5.1B active)Q2_K54.2 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 90B Vision InstructMeta · 89BQ2_K42.0 GB—Won't run
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Command R+ 104B (04-2024)Cohere · 104BQ2_K46.8 GB—Won't run
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2 ChatDeepSeek · 236B (21.0B active)Q2_K98.0 GB—Won't run
38Basic quality (D) · 38 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.Mixtral 8x22B InstructMistral AI · 141B (39.0B active)Q2_K61.3 GB—Won't run
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 110B ChatAlibaba · 111BQ2_K50.3 GB—Won't run
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Grok-1 (314B)xAI · 314B (86.0B active)Q2_K131 GB—Won't run
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Snowflake Arctic InstructSnowflake · 479B (17.0B active)Q2_K195 GB—Won't run
23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking.Falcon 180B ChatTII · 180BQ2_K75.3 GB—Won't run

Image models on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.Krea 2 TurboKrea · 12.8BFP820.2 GB8.5 sRuns great
91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.FLUX 3 Image KleinBlack Forest Labs · 5.6BFP1622.4 GB13 sRuns great
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-Image TurboBaidu · 8.0BFP1626.4 GB7.1 sRuns great
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Z-Image TurboAlibaba (Tongyi) · 6.2BFP1622.7 GB5.5 sRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 9BBlack Forest Labs · 9.1BQ8 GGUF20.5 GB4.6 sRuns great
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 4BBlack Forest Labs · 3.9BFP1618.1 GB2.2 sRuns great
87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2.1 TurboAlibaba · 7.1BFP830.8 GB23 sRuns welltight fit
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Fibo 2.0 DevBria AI · 8.1BFP1627.7 GB50 sSlowtight fit
69Good quality (B) · 69 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [schnell]Black Forest Labs · 11.9BQ8 GGUF20.4 GB5.1 sRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Ideogram 4Ideogram · 18.6BFP829.9 GB50 sSlowtight fit
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Krea [dev]Black Forest Labs · 11.9BFP819.6 GB24 sRuns well
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Z-ImageAlibaba (Tongyi) · 6.2BFP1622.7 GB37 sRuns well
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-ImageBaidu · 8.0BFP818.3 GB44 sSlow
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [dev]Black Forest Labs · 11.9BFP819.6 GB24 sRuns well
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Kontext [dev]Black Forest Labs · 11.9BFP820.2 GB44 sSlow
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Fill [dev]Black Forest Labs · 11.9BFP819.6 GB25 sRuns well
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.MOSS-Image SFTOpenMOSS · 5.1BFP815.8 GB28 sRuns well
70Great quality (A) · 70 of 100: how capable the model is at NF4, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FastHiDream.ai · 17.1BNF426.2 GB24 sRuns well
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Ming-Image 0.1 DesignAnt Group (inclusionAI) · 6.2BFP1626.8 GB38 sRuns wellencoder unloaded after use
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.KolorsKuaishou · 2.6BFP1619.8 GB8.8 sRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2512Alibaba · 20.4BQ4 GGUF26.9 GB4.0 minVery slow
61Good quality (B) · 61 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 Large TurboStability AI · 8.1BQ8 GGUF16.8 GB4.1 sRuns great
78Great quality (A) · 78 of 100: how capable the model is at NF4, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FullHiDream.ai · 17.1BNF426.2 GB1.8 minSlow
80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.FireRed-Image-Edit 1.1rednote (FireRed Team) · 20.4BQ4 GGUF24.3 GB3.5 minVery slow
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image-Edit 2511Alibaba · 20.4BQ4 GGUF24.3 GB3.5 minVery slow
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Chroma1-HDLodestone Rock · 8.9BFP816.4 GB40 sRuns well
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [dev]Black Forest Labs · 32.2BQ4 GGUF22.8 GB1.7 minSlowencoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Iris-3BSperidlabs · 3.0BFP1617.3 GB35 sRuns well
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 DevHiDream.ai · 17.1BFP820.1 GB35 sRuns wellencoder unloaded after use
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qwen-ImageAlibaba · 20.4BFP826.8 GB3.1 minVery slowencoder unloaded after use
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.CogView4 6BZhipu AI · 6.4BFP818.2 GB36 sRuns well
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 LargeStability AI · 8.1BFP816.3 GB22 sRuns well
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3 MediumStability AI · 2.0BFP1617.4 GB6.8 sRuns great
66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.OmniGen2BAAI (VectorSpaceLab) · 4.0BFP1618.0 GB35 sRuns well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2.1Alibaba · 7.1BQ4 GGUF29.5 GB2.8 minVery slowtight fit · encoder unloaded after use
62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Juggernaut XL v9RunDiffusion · 2.6BFP168.9 GB9.9 sRuns great
62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.RealVisXL V5.0SG161222 · 2.6BFP168.9 GB9.9 sRuns great
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Animagine XL 4.0Cagliostro Lab · 2.6BFP168.9 GB9.3 sRuns great
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Illustrious XL v0.1OnomaAI · 2.6BFP168.9 GB9.3 sRuns great
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.AuraFlow v0.3fal · 6.9BFP1618.5 GB31 sRuns well
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.DreamShaper XL v2 TurboLykon · 2.6BFP168.9 GB2.9 sRuns great
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Pony Diffusion V6 XLPurpleSmartAI · 2.6BFP168.9 GB8.4 sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Kandinsky 3Sber AI · 3.0BFP1625.9 GB20 sRuns well
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Cosmos3-Super Text2Image (64B)NVIDIA · 64.0BFP826.1 GB1.7 minSlowCPU offload
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 MediumStability AI · 2.5BFP810.4 GB12 sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.PixArt-Σ XL 1024PixArt · 0.6BFP1612.8 GB3.3 sRuns great
56Good quality (B) · 56 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Animagine XL 3.1Cagliostro Lab · 2.6BFP168.9 GB9.3 sRuns great
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion XL 1.0Stability AI · 2.6BFP168.9 GB9.9 sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.SDXL-Lightning (4-step)ByteDance · 2.6BFP168.9 GB1.5 sRuns great
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Lumina-Image 2.0Shanghai AI Lab · 2.6BFP87.5 GB14 sRuns well
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Stable CascadeStability AI · 5.2BFP88.1 GB9.9 sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan-DiT v1.2Tencent · 1.5BFP169.3 GB13 sRuns great
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Playground v2.5Playground AI · 2.6BFP85.6 GB15 sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.SDXL TurboStability AI · 2.6BFP167.6 GB0.3 sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Realistic Vision V5.1SG161222 · 0.9BFP162.8 GB2.6 sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.DreamShaper 8Lykon · 0.9BFP162.8 GB2.6 sRuns great
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 1.5Stability AI / Runway · 0.9BFP162.8 GB2.6 sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.LCM DreamShaper v7Tsinghua (LCM) · 0.9BFP162.8 GB0.6 sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.SD TurboStability AI · 0.9BFP163.3 GB0.2 sRuns great
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.HunyuanImage 3.0 (80B-A13B)Tencent · 83.0BFP832.8 GB—Won't run

Video models on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Quality Model Quant Memory Speed Runs
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.LTX-2.5 (22B, video + audio)Lightricks · 21.0BQ4 GGUF26.8 GB4.2 minRuns wellencoder unloaded after use
66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0BFP830.1 GB2.0 minRuns welltight fit
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Bernini-R A14B (video generation + editing)ByteDance · 14.3BFP826.0 GB23.8 minSlow
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.HY-OmniWeaving (8.3B, unified video)Tencent · 8.3BFP824.6 GB17.5 minSlow
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9BFP828.2 GB13.2 minSlowtight fit
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.SCAIL-2 14B (character animation)Zhipu AI · 16.4BFP829.8 GB39.7 minSlowtight fit
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 480PAlibaba · 14.0BFP826.2 GB29.8 minSlow
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.LTX-2.3Lightricks · 18.9BQ4 GGUF24.5 GB18.5 minSlowencoder unloaded after use
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3BFP828.1 GB33.1 minSlowtight fit
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.LTX-2 (19B, video + audio)Lightricks · 18.9BQ4 GGUF24.5 GB18.5 minSlowencoder unloaded after use
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.LTX-Video 2BLightricks · 1.9BFP1617.5 GB55 sRuns great
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0BFP826.8 GB8.3 minRuns well
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 T2V 14B 540PSkywork · 14.0BFP829.3 GB46.3 minVery slowtight fit
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 I2V A14BAlibaba · 14.0BQ4 GGUF27.0 GB74.1 minVery slowencoder unloaded after use
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 T2V A14BAlibaba · 14.0BQ4 GGUF27.0 GB74.1 minVery slowencoder unloaded after use
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo 1.5 (8.3B)Tencent · 8.3BFP829.9 GB62.5 minVery slowtight fit · encoder unloaded after use
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 VACE 1.3BAlibaba · 2.2BFP1621.5 GB9.6 minRuns well
45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 2BZhipu AI · 1.7BFP1617.5 GB2.2 minRuns great
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 T2V 1.3BAlibaba · 1.3BFP1619.8 GB8.8 minRuns well
65Good quality (B) · 65 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 TI2V 5BAlibaba · 5.0BQ4 GGUF30.4 GB22.9 minSlowtight fit
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Mochi 1 Preview (10B)Genmo · 10.0BFP826.7 GB36.4 minSlow
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4BFP1623.8 GB11.0 minRuns well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5B I2VZhipu AI · 5.6BFP814.9 GB6.0 minRuns well
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.MiniMax H3 (33B, video + audio)MiniMax · 20.1BFP822.4 GB44.7 minVery slowCPU offload
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 720PAlibaba · 14.0BQ4 GGUF27.0 GB1.5 hVery slowencoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 T2V 14BAlibaba · 14.0BQ4 GGUF27.0 GB1.5 hVery slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5BZhipu AI · 5.0BFP814.3 GB6.0 minRuns well
68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI · 3.2BFP1614.7 GB12.0 minRuns wellencoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 Animate 14BAlibaba · 17.3BQ4 GGUF28.3 GB87.9 minVery slowtight fit · encoder unloaded after use
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 VACE 14BAlibaba · 17.3BQ4 GGUF29.0 GB1.7 hVery slowtight fit · encoder unloaded after use
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Kandinsky 6.0 Pro (29B, video + audio)Sber AI · 30.1BFP1627.8 GB2.3 hVery slowtight fit · CPU offload
66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo 13BTencent · 13.0BQ4 GGUF30.4 GB1.9 hVery slowtight fit · encoder unloaded after use
66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo I2V 13BTencent · 13.0BQ4 GGUF30.4 GB1.9 hVery slowtight fit · encoder unloaded after use
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 T2V 14B 720PSkywork · 14.0BFP826.0 GB1.7 hVery slowCPU offload
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Step-Video T2V (30B)StepFun · 30.0BFP825.0 GB2.2 hVery slowCPU offload
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0BFP824.7 GB68.8 minVery slowCPU offload
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Allegro (2.8B)Rhymes AI · 2.8BFP1628.7 GB46.3 minVery slowtight fit · encoder unloaded after use
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Open-Sora 2.0 (11B)HPC-AI Tech · 11.0BFP1619.3 GB2.4 hVery slowCPU offload
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3BFP164.7 GB44 sRuns great
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0BFP1629.2 GB26.3 minSlowtight fit · CPU offload
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 1.5 5BZhipu AI · 5.6BFP831.2 GB38.7 minSlowtight fit · CPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Cosmos3-Super Image2Video (64B)NVIDIA · 64.0BFP1653.7 GB—Won't run
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.Wan-Dancer 14B (music to dance)Alibaba · 17.3BFP835.6 GB—Won't run

Decision models on the NVIDIA RTX Spark N1X (6144-core GPU) (48 GB)

Quality Model Quant Memory Speed Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 4BAlibaba · 4.0BQ8_07.7 GB125 msRuns great
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v3.5Jina AI · 600MF164.6 GB26 msRuns great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.zerank-2ZeroEntropy · 4.0BQ8_07.7 GB125 msRuns great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Intern-Decision 4BShanghai AI Lab · 4.5BQ8_08.1 GB84 msRuns great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v3Jina AI · 600MF164.6 GB26 msRuns great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Shieldstral 1.0 3BMistral AI · 3.9BQ8_07.5 GB120 msRuns great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.d1 3BLiquid AI · 3.1BF169.4 GB79 msRuns great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.mxbai-rerank-large v2Mixedbread · 1.5BF166.3 GB60 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.FRIDA-DecisionsSber AI · 820MF162.4 GB17 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.GLiNER2.5 DecideFastino · 490MF161.7 GB12 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.LemonDecider 4BAnt Group (inclusionAI) · 4.5BF1610.8 GB74 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 0.6BAlibaba · 600MF164.6 GB26 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.zerank-1 smallZeroEntropy · 1.7BF166.8 GB66 msRuns great
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.BGE Reranker v2 GemmaBAAI · 2.5BF168.2 GB95 msRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 8BAlibaba · 8.2BQ8_012.2 GB250 msRuns well
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 86MMeta · 280MF161.2 GB13 msRuns great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.mxbai-rerank-base v2Mixedbread · 490MF164.2 GB22 msRuns great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.GLiClass ModernBERT Large v3Knowledgator · 400MF161.5 GB10 msRuns great
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.OpenAI Privacy FilterOpenAI · 1.4B (50M active)F163.8 GB4.8 msRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Skywork Reward V2 Llama 3.1 8BSkywork · 7.5BQ8_010.4 GB407 msSlow
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.BGE Reranker v2 M3BAAI · 570MF161.9 GB22 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.DeBERTa v3 Large Zero-shot v2.0Moritz Laurer · 440MF161.6 GB11 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.DuoGuard 0.5BDuoGuard · 490MF161.7 GB19 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Skywork Reward V2 Qwen3 0.6BSkywork · 600MF162.0 GB41 msRuns great
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.GTE Reranker ModernBERT BaseAlibaba · 150MF160.9 GB8.6 msRuns great
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v2 Base MultilingualJina AI · 280MF161.2 GB13 msRuns great
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.ModernBERT Large Zero-shot v2.0Moritz Laurer · 400MF161.5 GB10 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.GLiGuard 300MFastino · 210MF161.1 GB10 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Granite Embedding Reranker English R2IBM · 150MF160.9 GB8.6 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.LayaConvai Innovations · 420MF161.5 GB10 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 22MMeta · 71MF160.8 GB6.2 msRuns great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Qwen3Guard Gen 0.6BAlibaba · 750MF164.9 GB75 msRuns great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Skywork Reward V2 Qwen3 8BSkywork · 7.6BQ8_010.5 GB410 msSlow
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.GLiClass Base v3Knowledgator · 190MF161.0 GB6.9 msRuns great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.ProtectAI DeBERTa v3 Prompt Injection v2Protect AI · 180MF161.0 GB9.6 msRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Qwen3Guard Gen 4BAlibaba · 4.4BQ6_K7.1 GB216 msRuns well
64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.DeBERTa v3 Base Zero-shot v2.0Moritz Laurer · 180MF161.0 GB6.8 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.GLiNER2 Base v1Fastino · 210MF161.1 GB7.2 msRuns great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.HHEM 2.1 OpenVectara · 110MF160.8 GB11 msRuns great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Qwen3Guard Gen 8BAlibaba · 8.2BQ6_K10.2 GB399 msRuns well
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.LettuceDetect LargeKR Labs · 400MF161.5 GB29 msRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 8.0BQ6_K10.0 GB391 msRuns well
60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Laya MultilingualConvai Innovations · 320MF161.3 GB8.9 msRuns great
81Great quality (A) · 81 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Granite Guardian 4.1 8BIBM · 8.4BQ5_K_M9.5 GB376 msRuns well
58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 2BGoogle · 2.6BF168.6 GB99 msRuns great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.GLiNER Multi v2.1Urchade Zaratiana · 290MF161.3 GB8.5 msRuns great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.WildGuard 7BAi2 · 7.3BQ6_K9.4 GB353 msRuns well
56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.BART Large MNLIMeta · 410MF161.5 GB10 msRuns great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Granite Guardian 3.3 8BIBM · 8.2BQ6_K10.2 GB398 msRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.NuExtract 2.0 2BNuMind · 2.2BQ4_K_M4.6 GB175 msRuns well
73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.NuExtract 2.0 4BNuMind · 3.8BQ5_K_M5.9 GB346 msRuns well
52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.ms-marco MiniLM L6 v2Sentence Transformers · 23MF160.7 GB4.7 msRuns great
64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 9BGoogle · 9.2BQ8_013.7 GB281 msRuns well
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Llama Guard 3 1BMeta · 1.5BQ8_04.8 GB89 msRuns great
67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Llama Guard 3 8BMeta · 8.0BQ6_K10.0 GB391 msRuns well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 27BGoogle · 27BQ6_K26.2 GB782 msSlow
83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.CompassJudger-2 32BOpenCompass · 33BQ5_K_M27.0 GB17.8 sVery slow
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Llama Guard 4 12BMeta · 12BQ6_K13.4 GB582 msSlow
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Content Safety Reasoning 4BNVIDIA · 4.3BQ6_K7.0 GB2.8 sVery slow
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 20BOpenAI · 22B (3.6B active)MXFP415.5 GB2.1 sVery slow
79Great quality (A) · 79 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.DynaGuard 8BUniversity of Maryland · 8.2BQ8_012.2 GB7.2 sVery slow
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Selene 1 Mini 8BAtla · 8.0BQ8_012.0 GB6.8 sVery slow
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.CompassJudger-2 7BOpenCompass · 7.6BQ8_011.4 GB6.5 sVery slow
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.DynaGuard 1.7BUniversity of Maryland · 2.0BQ6_K5.1 GB1.3 sSlow
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Prometheus 2 7BPrometheus Eval · 7.2BQ8_011.1 GB6.2 sVery slow
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Prometheus 2 8x7BPrometheus Eval · 47B (13B active)Q4_K_M31.9 GB6.4 sVery slowtight fit
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.GLIDERPatronus AI · 3.8BQ6_K7.1 GB2.4 sVery slow
63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Flow Judge v0.1Flow AI · 3.8BQ6_K7.1 GB2.4 sVery slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 27BFastino · 26BQ8_034.8 GB—Won't run
80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 120BOpenAI · 117B (5.1B active)MXFP469.8 GB—Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 466 of 619 LLMs run well on your NVIDIA RTX Spark N1X (6144-core GPU) (48 GB).

Intel Arc Pro B70 Cheapest upgrade Intel Arc Pro B70 32.0 GB · $949 launch price +18 LLMs run well, including Qwen3-Next 80B-A3B Thinking
NVIDIA RTX PRO 6000 Blackwell Workstation Edition Biggest jump NVIDIA RTX PRO 6000 Blackwell 96.0 GB · $8,565 launch price +80 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.

Was this page helpful?