What the Intel Xeon Silver (4100 to 4300 series) NAS (64 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
64.0 GB
Usable for models
54.4 GB
Memory bandwidth
115 GB/s
FP16 compute
1.0 TFLOPS
519 / 619 LLMs run Best: Kolibri 1 (78B-A3.5B) (A+) 60 / 60 Image models run Best: Krea 2 Turbo (A+) 42 / 43 Video models run Best: LTX-2.5 (22B, video + audio) (A+) 69 / 70 Decision models run Best: OpenAI Privacy Filter (A)

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

LLMs on the Intel Xeon Silver (4100 to 4300 series) NAS (64 GB)

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 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.Kolibri 1 (78B-A3.5B)Aleph Alpha · 78B (3.5B active)Q4_K_M52.8 GB18.6 tok/sRuns welltight fit
85Excellent quality (A+) · 85 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.Flint (40B-A2.5B)Recursive · 40B (2.5B active)Q4_K_M29.5 GB25.1 tok/sRuns well
88Excellent quality (A+) · 88 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.Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
88Excellent quality (A+) · 88 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.Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
88Excellent quality (A+) · 88 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.MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active)Q4_K_M26.6 GB21.2 tok/sRuns well
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active)Q4_K_M53.8 GB21.2 tok/sRuns welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active)Q4_K_M26.5 GB21.2 tok/sRuns well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Sage-A1.5 35B-A3BInternScience · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
86Excellent quality (A+) · 86 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.KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active)Q4_K_M26.3 GB21.2 tok/sRuns well
85Excellent quality (A+) · 85 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.Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 26B-A4BGoogle · 26B (3.8B active)Q6_K26.5 GB12.0 tok/sRuns well
84Great quality (A) · 84 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.Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
84Great quality (A) · 84 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.Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M27.0 GB21.2 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)Q3_K_M45.0 GB27.0 tok/sRuns well
82Great quality (A) · 82 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.Agents-A1 35B-A3BInternScience · 35B (3.0B active)Q4_K_M26.5 GB21.2 tok/sRuns well
82Great quality (A) · 82 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.Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)Q4_K_M26.3 GB21.2 tok/sRuns well
87Excellent quality (A+) · 87 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.Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active)Q6_K28.6 GB10.6 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active)Q3_K_M45.0 GB27.0 tok/sRuns well
83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)Q4_K_M24.4 GB21.2 tok/sRuns well
80Great quality (A) · 80 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.Hunyuan Hy-Memory 30B-A3BTencent · 30B (3.0B active)Q4_K_M24.1 GB21.2 tok/sRuns well
70Great quality (A) · 70 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.Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)Q4_K_M35.0 GB21.2 tok/sRuns well
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.Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)Q4_K_M26.7 GB21.2 tok/sRuns well
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)Q4_K_M23.8 GB21.2 tok/sRuns well
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M24.3 GB18.4 tok/sRuns well
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.Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)Q4_K_M24.4 GB19.4 tok/sRuns well
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.Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M24.4 GB19.4 tok/sRuns well
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)Q4_K_M24.4 GB19.4 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)Q4_K_M24.7 GB19.4 tok/sRuns well
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M24.3 GB18.4 tok/sRuns well
70Great quality (A) · 70 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.Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)Q4_K_M24.7 GB19.4 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Sarvam 30BSarvam AI · 32B (2.4B active)Q4_K_M24.7 GB26.1 tok/sRuns well
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50BQ5_K_M43.0 GB1.1 tok/sVery slow
70Great quality (A) · 70 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.Qwen3 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M24.4 GB19.4 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Maple Preview (20B-A1B)DeepGrove · 20B (1.5B active)Q4_K_M17.4 GB39.9 tok/sRuns great
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Bolt 74B-A9BNVIDIA · 75B (9.0B active)Q2_K35.0 GB12.1 tok/sRuns well
70Great quality (A) · 70 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.LFM2.5 24B-A2BLiquid AI · 24B (2.5B active)Q4_K_M19.7 GB25.6 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.Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)Q4_K_M24.3 GB21.2 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)Q4_K_M27.3 GB19.4 tok/sRuns well
74Great quality (A) · 74 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.DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)Q4_K_M21.1 GB16.2 tok/sRuns well
75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 38BShanghai AI Lab · 38BQ6_K38.6 GB1.2 tok/sVery slow
76Great quality (A) · 76 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.Kimi Dev 72BMoonshot AI · 73BQ4_K_M52.0 GB0.9 tok/sVery slowtight fit
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active)Q2_K53.6 GB13.5 tok/sRuns welltight fit
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active)Q2_K52.9 GB17.7 tok/sRuns welltight fit
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss 20BOpenAI · 21B (3.6B active)MXFP417.1 GB19.1 tok/sRuns well
62Good quality (B) · 62 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.Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)Q3_K_M45.4 GB6.7 tok/sSlow
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 38BShanghai AI Lab · 38BQ6_K38.6 GB1.2 tok/sVery slow
66Good quality (B) · 66 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.ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)Q4_K_M18.7 GB21.2 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Axion 1.0 35BAxion · 35B (3.0B active)Q4_K_M26.5 GB21.2 tok/sRuns well
54Fair quality (C) · 54 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.Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K46.6 GB17.5 tok/sRuns welltight fit
80Great quality (A) · 80 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.Qwen3.8 27BAlibaba · 28BQ3_K_M19.1 GB3.2 tok/sSlow
82Great quality (A) · 82 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 12BGoogle · 12BQ6_K15.4 GB4.0 tok/sSlow
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.Ling 2.6 Flash (104B-A7.4B)Ant Group (inclusionAI) · 107B (7.4B active)Q2_K48.0 GB14.5 tok/sRuns welltight fit
62Good quality (B) · 62 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.Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)Q4_K_M21.1 GB21.2 tok/sRuns well
70Great quality (A) · 70 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.Hermes 4 70BNous Research · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
70Great quality (A) · 70 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.Llama 3.3 70B InstructMeta · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
78Great quality (A) · 78 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.Qwen3.6 27BAlibaba · 28BQ3_K_M19.1 GB3.2 tok/sSlow
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K46.6 GB17.5 tok/sRuns welltight fit
69Good quality (B) · 69 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 72B InstructAlibaba · 73BQ4_K_M52.0 GB0.9 tok/sVery slowtight fit
69Good quality (B) · 69 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-VL 72B InstructAlibaba · 73BQ4_K_M52.4 GB0.9 tok/sVery slowtight fit
78Great quality (A) · 78 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.Qwen3.5 27BAlibaba · 28BQ3_K_M19.1 GB3.2 tok/sSlow
56Good quality (B) · 56 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.NorthCUA Minibeipo-ai · 35B (3.0B active)Q4_K_M26.5 GB21.2 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.6VZhipu AI · 108B (12.0B active)Q2_K49.6 GB9.1 tok/sSlowtight fit
68Good quality (B) · 68 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.DeepSeek R1 Distill Llama 70BDeepSeek · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
68Good quality (B) · 68 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.Tülu 3 70BAi2 · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
66Good quality (B) · 66 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.Mellum2.1 Thinking (12B-A2.5B)JetBrains · 12B (2.5B active)Q4_K_M12.5 GB25.1 tok/sRuns well
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Leanstral 119B-A6BMistral AI · 119B (6.5B active)Q2_K52.9 GB16.4 tok/sRuns welltight fit
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5VZhipu AI · 108B (12.0B active)Q2_K49.6 GB9.1 tok/sSlowtight fit
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Solar Open 100BUpstage · 103B (12.0B active)Q2_K47.6 GB9.1 tok/sSlowtight fit
75Great quality (A) · 75 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.TMax 27BAi2 · 27BQ3_K_M18.9 GB3.2 tok/sSlow
60Good quality (B) · 60 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.ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)Q4_K_M18.8 GB21.2 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 70B InstructMeta · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Groot 65B A6B 261023GrootTeam · 118B (6.0B active)Q2_K52.5 GB17.7 tok/sRuns welltight fit
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)Q2_K50.7 GB9.1 tok/sSlowtight fit
73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Fara 1.5 27BMicrosoft · 27BQ3_K_M18.9 GB3.2 tok/sSlow
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 78BShanghai AI Lab · 78BQ3_K_M46.1 GB1.1 tok/sVery slow
52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Sarvam 105BSarvam AI · 106B (10.0B active)Q2_K47.7 GB10.9 tok/sRuns welltight fit
64Good quality (B) · 64 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.Hermes 3 (Llama 3.1 70B)Nous Research · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
64Good quality (B) · 64 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.QVQ 72B PreviewAlibaba · 73BQ4_K_M52.4 GB0.9 tok/sVery slowtight fit
58Good quality (B) · 58 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.Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)Q5_K_M10.8 GB37.8 tok/sRuns great
53Fair quality (C) · 53 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.Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)Q4_K_M31.6 GB10.0 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.UI-Mate 27BTencent · 27BQ3_K_M18.9 GB3.2 tok/sSlow
53Fair quality (C) · 53 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.LFM2 24B-A2BLiquid AI · 24B (2.3B active)Q4_K_M19.7 GB27.1 tok/sRuns well
62Good quality (B) · 62 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.Llama 3.1 Nemotron 70B InstructNVIDIA · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
62Good quality (B) · 62 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.Apertus v1.5 70BSwiss AI · 72BQ4_K_M51.6 GB1.0 tok/sVery slowtight fit
71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Apriel 1.5 15B ThinkerServiceNow · 15BQ6_K18.7 GB3.2 tok/sSlow
71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning Plus (14B)Microsoft · 15BQ6_K18.7 GB3.2 tok/sSlow
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.Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)Q4_K_M15.2 GB42.1 tok/sRuns great
60Good quality (B) · 60 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 72B InstructAlibaba · 73BQ4_K_M52.0 GB0.9 tok/sVery slowtight fit
60Good quality (B) · 60 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-VL 72B InstructAlibaba · 73BQ4_K_M52.4 GB0.9 tok/sVery slowtight fit
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning Vision 15BMicrosoft · 15BQ6_K19.0 GB3.1 tok/sSlow
66Good quality (B) · 66 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.Nemotron 3.5 Bolt E4BNVIDIA · 8.0BQ4_K_M10.0 GB15.2 tok/sRuns well
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning (14B)Microsoft · 15BQ6_K18.7 GB3.2 tok/sSlow
57Good quality (B) · 57 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.Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)Q4_K_M15.2 GB21.2 tok/sRuns well
66Good quality (B) · 66 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.Nanbeige4.3 33BBOSS Zhipin (Nanbeige) · 33BQ2_K19.9 GB3.4 tok/sSlow
58Good quality (B) · 58 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.Gemma 4 E2BGoogle · 5.1BQ4_K_M8.1 GB29.8 tok/sRuns well
50Fair quality (C) · 50 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.Llama 4 Scout 17B-16EMeta · 109B (17.0B active)Q2_K50.0 GB6.5 tok/sSlowtight fit
51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)Q6_K44.3 GB3.6 tok/sSlow
64Good quality (B) · 64 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.Gemma 4 E4BGoogle · 8.0BQ4_K_M10.0 GB15.2 tok/sRuns well
54Fair quality (C) · 54 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.Groot 19B A3B 261023GrootTeam · 19B (3.0B active)Q4_K_M17.0 GB21.2 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Nanbeige4.2 3BBOSS Zhipin (Nanbeige) · 4.2BQ4_K_M9.0 GB16.5 tok/sRuns well
67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 14BAlibaba · 15BQ6_K18.4 GB3.2 tok/sSlow
64Good quality (B) · 64 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.Nemotron Labs Dory 1.0 4BNVIDIA · 4.0BQ4_K_M7.8 GB17.2 tok/sRuns well
57Good quality (B) · 57 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.Command A Reasoning (111B)Cohere · 111BQ2_K50.1 GB1.0 tok/sVery slowtight fit
47Fair quality (C) · 47 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.Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)Q4_K_M36.5 GB5.6 tok/sSlow
57Good quality (B) · 57 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 70B InstructSwiss AI · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
63Good quality (B) · 63 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.Granite 4.2 30BIBM · 29BQ3_K_M21.4 GB3.0 tok/sSlow
49Fair quality (C) · 49 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.Mixtral 8x7B InstructMistral AI · 47B (12.9B active)Q6_K44.3 GB3.6 tok/sSlow
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.Apriel Nemotron 15B ThinkerServiceNow · 15BQ6_K18.9 GB3.2 tok/sSlow
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Command A (111B)Cohere · 111BQ2_K50.1 GB1.0 tok/sVery slowtight fit
47Fair quality (C) · 47 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.Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)Q4_K_M40.4 GB4.8 tok/sSlow
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.AceReason Nemotron 14BNVIDIA · 15BQ6_K18.7 GB3.2 tok/sSlow
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.OpenReasoning Nemotron 14BNVIDIA · 15BQ6_K18.7 GB3.2 tok/sSlow
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.Qwen2.5 Coder 14B InstructAlibaba · 15BQ6_K18.7 GB3.2 tok/sSlow
49Fair quality (C) · 49 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.LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)Q4_K_M10.2 GB39.6 tok/sRuns great
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.Hermes 4 14BNous Research · 15BQ6_K18.4 GB3.2 tok/sSlow
53Fair quality (C) · 53 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.LFM3 1.7BLiquid AI · 1.7BQ4_K_M6.1 GB39.7 tok/sRuns great
55Good quality (B) · 55 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.Llama 3.2 90B Vision InstructMeta · 89BQ3_K_M51.7 GB1.0 tok/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.Ministral 3 14B ReasoningMistral AI · 14BQ6_K17.7 GB3.4 tok/sSlow
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 31BGoogle · 31BQ2_K19.1 GB3.6 tok/sSlow
62Good quality (B) · 62 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.Spark-X2.6 4BSparkLLM · 4.1BQ4_K_M7.8 GB16.7 tok/sRuns well
55Good quality (B) · 55 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.Llama 3 70B InstructMeta · 71BQ4_K_M50.7 GB1.0 tok/sVery slowtight fit
55Good quality (B) · 55 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.Qwen2.5-Math 72B InstructAlibaba · 73BQ4_K_M50.6 GB0.9 tok/sVery slowtight fit
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 2 (24B)Mistral AI · 24BQ3_K_M18.1 GB3.7 tok/sSlow
57Good quality (B) · 57 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.MiniCPM5 2BOpenBMB · 2.5BQ4_K_M6.8 GB27.2 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Muse Glimmer 30BMeta · 30BQ2_K17.0 GB3.8 tok/sSlow
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.InternVL3 14BShanghai AI Lab · 15BQ6_K19.0 GB3.1 tok/sSlow
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.Phi-4 (14B)Microsoft · 15BQ6_K18.7 GB3.2 tok/sSlow
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.DeepCoder 14B PreviewAgentica · 15BQ6_K18.7 GB3.2 tok/sSlow
49Fair quality (C) · 49 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.DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)Q4_K_M14.8 GB26.1 tok/sRuns well
62Good quality (B) · 62 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.Reka Flash 3.1 (21B)Reka AI · 21BQ4_K_M18.8 GB3.3 tok/sSlow
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.Ministral 3 14BMistral AI · 14BQ6_K17.7 GB3.4 tok/sSlow
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 30BIBM · 29BQ3_K_M21.2 GB3.1 tok/sSlow
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 14BDeepSeek · 15BQ6_K18.7 GB3.2 tok/sSlow
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 14B InstructAlibaba · 15BQ6_K18.6 GB3.2 tok/sSlow
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.JanusCoder 14BShanghai AI Lab · 15BQ6_K18.4 GB3.2 tok/sSlow
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 27B ITGoogle · 27BQ3_K_M19.2 GB3.2 tok/sSlow
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 1.2 (24B)Mistral AI · 24BQ3_K_M18.1 GB3.7 tok/sSlow
58Good quality (B) · 58 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.Codestral 22BMistral AI · 22BQ4_K_M20.4 GB3.1 tok/sSlow
43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)Q6_K10.7 GB40.6 tok/sRuns great
58Good quality (B) · 58 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.Qwen3.5 4BAlibaba · 4.7BQ4_K_M8.1 GB14.7 tok/sRuns well
57Good quality (B) · 57 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.TMax 4BAi2 · 4.2BQ4_K_M7.8 GB16.3 tok/sRuns well
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 14B Instruct 1MAlibaba · 15BQ6_K18.7 GB3.2 tok/sSlow
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 27B Text ITGoogle · 27BQ3_K_M19.0 GB3.3 tok/sSlow
47Fair quality (C) · 47 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.Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active)Q4_K_M15.2 GB21.2 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 1.1 (24B)Mistral AI · 24BQ3_K_M17.8 GB3.8 tok/sSlow
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 2507Mistral AI · 24BQ3_K_M17.8 GB3.8 tok/sSlow
44Fair quality (C) · 44 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.Unlimited OCR 2 (3B-A0.6B)Baidu · 3.3B (0.6B active)Q8_09.0 GB47.7 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Seed-OSS 36B InstructByteDance · 36BQ2_K21.6 GB3.1 tok/sSlow
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Command R+ (08-2024) 104BCohere · 104BQ2_K48.6 GB1.1 tok/sVery slowtight fit
57Good quality (B) · 57 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.Mage-VL-Cowork 4.7BMicrosoft · 4.7BQ4_K_M9.1 GB14.5 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.5 33BLG AI Research · 34BQ2_K19.4 GB3.3 tok/sSlow
57Good quality (B) · 57 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.Agents-A1 4BInternScience · 4.5BQ4_K_M8.0 GB15.1 tok/sRuns well
57Good quality (B) · 57 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 Pro Preview 22BUpstage · 22BQ4_K_M19.8 GB3.1 tok/sSlow
55Good quality (B) · 55 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4.3 36BNous Research · 36BQ2_K21.6 GB3.1 tok/sSlow
47Fair quality (C) · 47 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.LFM3-VL 2BLiquid AI · 1.9BQ4_K_M6.2 GB35.7 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Terminal RSI 27BTeriminal-RSI · 28BQ3_K_M19.1 GB3.2 tok/sSlow
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 12B ITGoogle · 12BQ6_K15.6 GB3.9 tok/sSlow
57Good quality (B) · 57 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.Mistral Small 3.2 24BMistral AI · 24BQ3_K_M18.1 GB3.7 tok/sSlow
57Good quality (B) · 57 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.Magistral Small 2506Mistral AI · 24BQ3_K_M17.8 GB3.8 tok/sSlow
57Good quality (B) · 57 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.Granite 4.2 8BIBM · 8.8BQ3_K_M10.6 GB10.1 tok/sRuns well
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.K2 Horizon 7BInstitute of Foundation Models · 9.0BQ2_K9.8 GB12.5 tok/sRuns well
55Good quality (B) · 55 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 22B V2LLM4Binary · 22BQ4_K_M20.4 GB3.1 tok/sSlow
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 32B InstructAlibaba · 33BQ2_K20.4 GB3.4 tok/sSlow
56Good quality (B) · 56 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.Hemmingway 1.5Hemmingway · 27BQ3_K_M18.7 GB3.3 tok/sSlow
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32BAlibaba · 33BQ2_K20.2 GB3.4 tok/sSlow
55Good quality (B) · 55 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.Fara 1.5 4BMicrosoft · 4.5BQ4_K_M8.0 GB15.1 tok/sRuns well
53Fair quality (C) · 53 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.Qwen3 4B Thinking 2507Alibaba · 4.0BQ4_K_M8.6 GB17.1 tok/sRuns well
55Good quality (B) · 55 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.SenseNova 6.8 Code2VideoSenseTime · 27BQ3_K_M18.9 GB3.2 tok/sSlow
55Good quality (B) · 55 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.Mistral Small 3.1 24BMistral AI · 24BQ3_K_M18.1 GB3.7 tok/sSlow
55Good quality (B) · 55 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.Devstral Small 2505Mistral AI · 24BQ3_K_M17.8 GB3.8 tok/sSlow
43Fair quality (C) · 43 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.Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)Q4_K_M14.9 GB21.2 tok/sRuns well
53Fair quality (C) · 53 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 32BAlibaba · 33BQ2_K20.2 GB3.4 tok/sSlow
53Fair quality (C) · 53 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.OpenReasoning Nemotron 32BNVIDIA · 33BQ2_K20.2 GB3.4 tok/sSlow
53Fair quality (C) · 53 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.Skywork OR1 32BSkywork · 33BQ2_K20.2 GB3.4 tok/sSlow
40Fair quality (C) · 40 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.Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)Q8_09.0 GB47.7 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL 4.7BMicrosoft · 4.7BQ4_K_M9.1 GB14.5 tok/sRuns well
44Fair quality (C) · 44 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.Command R+ 104B (04-2024)Cohere · 104BQ2_K48.6 GB1.1 tok/sVery slowtight fit
54Fair quality (C) · 54 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.SenseNova Loop 9B PreviewSenseTime · 9.7BQ2_K9.3 GB11.7 tok/sRuns well
54Fair quality (C) · 54 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.MiMo V2.6 Distill Qwen 9BXiaomi · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
51Fair quality (C) · 51 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.Qwen3 4B Instruct 2507Alibaba · 4.0BQ4_K_M8.6 GB17.1 tok/sRuns well
64Good quality (B) · 64 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.Ornith 1.5 122B-A10BDeepReinforce · 125B (10.0B active)Q2_K55.2 GB9.3 tok/sSlowover memory limit
53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3 24B (2501)Mistral AI · 24BQ3_K_M17.8 GB3.8 tok/sSlow
53Fair quality (C) · 53 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.Olmo 3.1 32B ThinkAi2 · 32BQ2_K18.6 GB3.5 tok/sSlow
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 27B ITGoogle · 27BQ3_K_M20.0 GB3.3 tok/sSlow
53Fair quality (C) · 53 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.Ornith 1.5 9BDeepReinforce · 9.7BQ2_K9.1 GB11.7 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.PaddleOCR-VL 1.6 0.9BBaidu · 1.0BQ6_K5.9 GB49.6 tok/sRuns great
51Fair quality (C) · 51 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.EXAONE Deep 32BLG AI Research · 32BQ2_K19.9 GB3.5 tok/sSlow
64Good quality (B) · 64 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.Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)Q2_K55.2 GB9.3 tok/sSlowover memory limit
51Fair quality (C) · 51 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.Qwen3-VL 4B InstructAlibaba · 4.4BQ4_K_M8.9 GB15.5 tok/sRuns well
65Good quality (B) · 65 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.Nemotron 3.5 Super VL 120B-A12BNVIDIA · 124B (12.0B active)Q2_K54.8 GB7.8 tok/sSlowover memory limit
51Fair quality (C) · 51 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.Mistral Small 22B (2409)Mistral AI · 22BQ4_K_M20.4 GB3.1 tok/sSlow
53Fair quality (C) · 53 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.Qwen3.5 9BAlibaba · 9.7BQ2_K9.1 GB11.7 tok/sRuns well
40Fair quality (C) · 40 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.MiniCPM-OCR 1.0 1.3BOpenBMB · 1.3BQ5_K_M6.0 GB43.6 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 3BIBM · 3.7BQ4_K_M7.9 GB18.7 tok/sRuns well
57Good quality (B) · 57 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.Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active)Q2_K56.3 GB17.6 tok/sRuns wellover memory limit
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Voxtral Small 24BMistral AI · 24BQ3_K_M18.2 GB3.7 tok/sSlow
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Dolphin Mistral 24B Venice EditionCognitive Computations · 24BQ3_K_M18.1 GB3.7 tok/sSlow
50Fair quality (C) · 50 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.DeepSeek R1 Distill Qwen 32BDeepSeek · 33BQ2_K20.2 GB3.4 tok/sSlow
52Fair quality (C) · 52 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.Ornith 1.0 9BDeepReinforce · 9.7BQ2_K9.1 GB11.7 tok/sRuns well
51Fair quality (C) · 51 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.GLM-4 32B 0414Zhipu AI · 33BQ2_K18.5 GB3.5 tok/sSlow
51Fair quality (C) · 51 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.GLM-Z1 32B (0414)Zhipu AI · 33BQ2_K18.5 GB3.5 tok/sSlow
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2BQ3_K_M10.2 GB10.8 tok/sRuns well
38Basic quality (D) · 38 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.DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)Q4_K_M14.8 GB26.1 tok/sRuns well
36Basic quality (D) · 36 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.LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)Q4_K_M10.1 GB39.6 tok/sRuns great
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 8BShanghai AI Lab · 8.5BQ3_K_M10.3 GB10.4 tok/sRuns well
51Fair quality (C) · 51 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.TMax 9BAi2 · 9.0BQ2_K8.8 GB12.6 tok/sRuns well
52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 8B InstructAlibaba · 8.8BQ3_K_M10.5 GB10.1 tok/sRuns well
43Fair quality (C) · 43 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.Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)Q2_K18.0 GB12.1 tok/sRuns well
38Basic quality (D) · 38 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.TeleOCRXingChen-AGI · 1.4BQ5_K_M6.9 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 60/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 70B InstructMeta · 69BQ4_K_M48.4 GB1.0 tok/sVery slowtight fit
49Fair quality (C) · 49 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.Qwen2.5 32B InstructAlibaba · 33BQ2_K20.2 GB3.4 tok/sSlow
49Fair quality (C) · 49 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.Baichuan M2 32BBaichuan · 33BQ2_K20.2 GB3.4 tok/sSlow
49Fair quality (C) · 49 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.OpenHands LM 32BAll Hands AI · 33BQ2_K20.2 GB3.4 tok/sSlow
50Fair quality (C) · 50 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.Olmo 3.1 32B InstructAi2 · 32BQ2_K18.6 GB3.5 tok/sSlow
50Fair quality (C) · 50 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.EXAONE 4.0 32BLG AI Research · 32BQ2_K18.5 GB3.5 tok/sSlow
50Fair quality (C) · 50 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.Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24BQ3_K_M17.8 GB3.8 tok/sSlow
47Fair quality (C) · 47 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.Qwen3 4BAlibaba · 4.0BQ4_K_M8.6 GB17.1 tok/sRuns well
50Fair quality (C) · 50 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.Qwen3 8BAlibaba · 8.2BQ3_K_M10.2 GB10.8 tok/sRuns well
50Fair quality (C) · 50 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.Granite 4.1 8BIBM · 8.8BQ3_K_M10.6 GB10.1 tok/sRuns well
50Fair quality (C) · 50 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.MiniCPM-V 4.5 8BOpenBMB · 8.7BQ3_K_M10.4 GB10.2 tok/sRuns well
38Basic quality (D) · 38 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.MiniCPM-V 4.7 1BOpenBMB · 1.6BQ4_K_M6.0 GB44.3 tok/sRuns great
47Fair quality (C) · 47 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.Qwen2.5-VL 32B InstructAlibaba · 33BQ2_K20.5 GB3.4 tok/sSlow
41Fair quality (C) · 41 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.North Micro VisionCohere · 2.5BQ4_K_M7.4 GB27.7 tok/sRuns well
47Fair quality (C) · 47 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.Nemotron 3 Nano 4BNVIDIA · 4.0BQ4_K_M7.5 GB17.3 tok/sRuns well
61Good quality (B) · 61 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.Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active)Q2_K54.5 GB7.8 tok/sSlowover memory limit
47Fair quality (C) · 47 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.Qianfan-OCR 4BBaidu · 4.7BQ4_K_M9.1 GB14.5 tok/sRuns well
46Fair quality (C) · 46 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.Qwen2.5 Coder 32B InstructAlibaba · 33BQ2_K20.2 GB3.4 tok/sSlow
49Fair quality (C) · 49 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.UI-Mate 9BTencent · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
49Fair quality (C) · 49 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.UI-Venus 2 9BAnt Group (inclusionAI) · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
38Basic quality (D) · 38 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.TMax 2BAi2 · 1.9BQ4_K_M6.2 GB36.5 tok/sRuns great
48Fair quality (C) · 48 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.MiMo-VL 7B RLXiaomi · 8.3BQ3_K_M10.2 GB10.7 tok/sRuns well
48Fair quality (C) · 48 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.Seed-Coder 8B ReasoningByteDance · 8.3BQ3_K_M10.1 GB10.8 tok/sRuns well
37Basic quality (D) · 37 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.Command R 35B (v01)Cohere · 35BQ2_K29.7 GB3.2 tok/sSlow
46Fair quality (C) · 46 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.QwQ 32B PreviewAlibaba · 33BQ2_K20.2 GB3.4 tok/sSlow
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 20B ChatShanghai AI Lab · 20BQ4_K_M18.7 GB3.5 tok/sSlow
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Mistral Nemo 12B InstructMistral AI · 12BQ4_K_M13.7 GB5.6 tok/sSlow
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E4BGoogle · 7.9BQ4_K_M9.9 GB17.2 tok/sRuns well
38Basic quality (D) · 38 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.DeepSeek LLM 67B ChatDeepSeek · 67BQ5_K_M54.4 GB0.8 tok/sVery slowtight fit
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 2.6BLiquid AI · 2.7BQ4_K_M6.7 GB25.4 tok/sRuns well
35Basic quality (D) · 35 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.MiniCPM5 1BOpenBMB · 1.1BQ6_K6.0 GB44.1 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 3BIBM · 3.4BQ4_K_M7.7 GB20.2 tok/sRuns well
47Fair quality (C) · 47 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.MiMo 7B RLXiaomi · 7.8BQ3_K_M10.0 GB11.3 tok/sRuns well
47Fair quality (C) · 47 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.EXAONE Deep 7.8BLG AI Research · 7.8BQ3_K_M9.9 GB11.3 tok/sRuns well
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8BQ4_K_M8.4 GB17.9 tok/sRuns well
47Fair quality (C) · 47 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.Seed-Coder 8B InstructByteDance · 8.3BQ3_K_M10.1 GB10.8 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.LightOnOCR-3 4BLightOn · 4.5BQ4_K_M8.0 GB15.1 tok/sRuns well
47Fair quality (C) · 47 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.Falcon-H1R 7BTII · 7.6BQ3_K_M9.0 GB11.7 tok/sRuns well
47Fair quality (C) · 47 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.InternVL3 8BShanghai AI Lab · 7.9BQ3_K_M9.3 GB11.2 tok/sRuns well
45Fair quality (C) · 45 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.Olmo 3 7B ThinkAi2 · 7.3BQ3_K_M10.0 GB12.2 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5-VL 3BLiquid AI · 3.1BQ4_K_M7.0 GB22.0 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 2BAlibaba · 2.3BQ4_K_M6.4 GB30.2 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E2BGoogle · 5.4BQ4_K_M8.4 GB34.3 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Pixtral 12B (2409)Mistral AI · 12BQ4_K_M13.9 GB5.5 tok/sSlow
44Fair quality (C) · 44 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.Falcon-H1 34B InstructTII · 34BQ2_K19.6 GB3.4 tok/sSlow
36Basic quality (D) · 36 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.Qwen1.5 110B ChatAlibaba · 111BQ2_K52.1 GB1.0 tok/sVery slowtight fit
46Fair quality (C) · 46 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.Qwen2.5 Coder 7B InstructAlibaba · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Jamba Reasoning 3BAI21 Labs · 3.2BQ4_K_M6.9 GB21.4 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Chandra OCR 2Datalab · 5.3BQ4_K_M8.5 GB12.9 tok/sRuns well
35Basic quality (D) · 35 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.Aya 23 35BCohere · 35BQ2_K29.7 GB3.2 tok/sSlow
45Fair quality (C) · 45 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.Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
45Fair quality (C) · 45 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.OpenReasoning Nemotron 7BNVIDIA · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini (3.8B)Microsoft · 3.8BQ4_K_M8.4 GB17.9 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.SmolLM3 3BHugging Face · 3.1BQ4_K_M7.4 GB22.3 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 3BMistral AI · 3.9BQ4_K_M8.2 GB17.8 tok/sRuns well
45Fair quality (C) · 45 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.MiniCPM4 8BOpenBMB · 8.2BQ3_K_M9.2 GB10.8 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Jamba2 3BAI21 Labs · 3.0BQ4_K_M6.8 GB22.6 tok/sRuns well
43Fair quality (C) · 43 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.Command R (08-2024) 32BCohere · 32BQ2_K19.2 GB3.5 tok/sSlow
42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.WeVisOne-VL 4BTencent · 4.8BQ4_K_M9.1 GB14.2 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 4B ITGoogle · 4.3BQ4_K_M7.8 GB16.0 tok/sRuns well
43Fair quality (C) · 43 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.Hunyuan 7B InstructTencent · 7.5BQ3_K_M9.7 GB11.8 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 2B InstructAlibaba · 2.1BQ4_K_M7.2 GB32.2 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 1.2B InstructLiquid AI · 1.2BQ6_K6.0 GB40.7 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5BQ4_K_M8.8 GB15.2 tok/sRuns well
43Fair quality (C) · 43 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.Foundation-Sec 8B ReasoningCisco Foundation AI · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 70B ChatMeta · 69BQ4_K_M48.4 GB1.0 tok/sVery slowtight fit
43Fair quality (C) · 43 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.Qwen2.5 7B InstructAlibaba · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 Mini InstructMicrosoft · 3.8BQ4_K_M10.5 GB18.0 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 4B ITGoogle · 4.3BQ4_K_M7.8 GB16.0 tok/sRuns well
42Fair quality (C) · 42 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.Aya Vision 32BCohere · 33BQ2_K19.6 GB3.4 tok/sSlow
42Fair quality (C) · 42 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.Aya Expanse 32BCohere · 32BQ2_K19.2 GB3.5 tok/sSlow
43Fair quality (C) · 43 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.Qwen2.5-VL 7B InstructAlibaba · 8.3BQ3_K_M9.5 GB10.7 tok/sRuns well
42Fair quality (C) · 42 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.Olmo 3 7B InstructAi2 · 7.3BQ3_K_M10.0 GB12.2 tok/sRuns well
47Fair quality (C) · 47 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.Ling 3.0 flash SanteAnt Group (inclusionAI) · 127B (5.1B active)Q2_K56.0 GB17.6 tok/sRuns wellover memory limit
42Fair quality (C) · 42 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.OLMo 2 32B InstructAi2 · 32BQ2_K18.9 GB3.5 tok/sSlow
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium 128K InstructMicrosoft · 14BQ4_K_M15.1 GB4.9 tok/sSlow
43Fair quality (C) · 43 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.MiniCPM-o 2.6 8BOpenBMB · 8.7BQ3_K_M9.7 GB10.2 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 4B InstructTencent · 4.2BQ4_K_M8.7 GB16.3 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 13B InstructAi2 · 14BQ4_K_M16.7 GB5.0 tok/sSlow
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Multimodal InstructMicrosoft · 5.6BQ4_K_M9.4 GB12.3 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 Micro (3B)IBM · 3.4BQ4_K_M7.7 GB20.2 tok/sRuns well
42Fair quality (C) · 42 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.Nemotron Nano 9B v2NVIDIA · 8.9BQ2_K8.6 GB12.7 tok/sRuns well
42Fair quality (C) · 42 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.DeepSeek R1 Distill Llama 8BDeepSeek · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
42Fair quality (C) · 42 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.Foundation-Sec 1.1 8B InstructCisco Foundation AI · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.InternVL2.5 8BShanghai AI Lab · 8.1BQ3_K_M10.0 GB11.0 tok/sRuns well
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium (14B)Microsoft · 14BQ4_K_M14.3 GB4.9 tok/sSlow
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B Instruct 1MAlibaba · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 7B InstructTII · 7.6BQ3_K_M9.0 GB11.7 tok/sRuns well
29Basic quality (D) · 29 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.EXAONE 4.0 1.2BLG AI Research · 1.3BQ5_K_M6.4 GB44.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.1V 9B ThinkingZhipu AI · 10BQ2_K9.4 GB11.0 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 9BFastino · 7.9BQ3_K_M9.1 GB11.2 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Fara 7BMicrosoft · 8.3BQ3_K_M9.5 GB10.7 tok/sRuns well
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.InternLM3 8B InstructShanghai AI Lab · 8.8BQ3_K_M9.7 GB10.1 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 Vision InstructMicrosoft · 4.2BQ4_K_M10.7 GB16.5 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.GLM-Z1 9B (0414)Zhipu AI · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Chat 20BShanghai AI Lab · 20BQ4_K_M18.7 GB3.5 tok/sSlow
40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 (Llama 3.1 8B)Nous Research · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 8B InstructMeta · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)Q4_K_M9.7 GB44.8 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H MicroIBM · 3.2BQ4_K_M7.0 GB21.5 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 8BMistral AI · 8.9BQ2_K9.7 GB12.6 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 2.6 8BOpenBMB · 8.1BQ3_K_M9.4 GB11.0 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 128K InstructMicrosoft · 3.8BQ4_K_M10.5 GB18.0 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.AFM 4.5BArcee AI · 4.6BQ4_K_M8.4 GB14.9 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.CogVLM2 Llama 3 Chat 19BZhipu AI · 20BQ4_K_M21.1 GB3.5 tok/sSlow
28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 1.7BAlibaba · 2.0BQ4_K_M7.1 GB33.8 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 7B InstructTII · 7.5BQ3_K_M9.5 GB11.9 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.LFM2 2.6BLiquid AI · 2.6BQ4_K_M6.7 GB26.7 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 3B InstructAlibaba · 3.1BQ4_K_M7.1 GB22.2 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 8B InstructIBM · 8.2BQ3_K_M10.3 GB10.9 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 8BIBM · 8.2BQ3_K_M10.3 GB10.9 tok/sRuns well
27Basic quality (D) · 27 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.Granite 4.0 H 1BIBM · 1.5BQ5_K_M6.1 GB38.8 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 7.8BLG AI Research · 7.8BQ3_K_M9.9 GB11.3 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Ministral 8B (2410)Mistral AI · 8.0BQ3_K_M10.1 GB11.1 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Tülu 3 8BAi2 · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 3B InstructTII · 3.2BQ4_K_M7.1 GB21.8 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 20BShanghai AI Lab · 20BQ4_K_M18.7 GB3.5 tok/sSlow
38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM3 4BOpenBMB · 4.1BQ4_K_M7.7 GB16.9 tok/sRuns well
33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 3B InstructMeta · 3.2BQ4_K_M7.8 GB21.4 tok/sRuns well
26Basic quality (D) · 26 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.Qwen3.5 0.8BAlibaba · 0.9BQ8_06.0 GB40.2 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 4K InstructMicrosoft · 3.8BQ4_K_M8.9 GB18.0 tok/sRuns well
60Good quality (B) · 60 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.Devstral 2 (123B)Mistral AI · 125BQ2_K57.9 GB0.8 tok/sVery slowover memory limit
25Basic quality (D) · 25 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.LFM2 1.2BLiquid AI · 1.2BQ6_K6.0 GB40.7 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Small 8K InstructMicrosoft · 7.4BQ3_K_M9.6 GB12.0 tok/sRuns well
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Prover V2 7BDeepSeek · 6.9BQ3_K_M12.4 GB12.8 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 8B InstructIBM · 8.2BQ3_K_M10.3 GB10.9 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Llama 3 8BNous Research · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.6 8BOpenChat · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 3B InstructAlibaba · 3.1BQ4_K_M7.1 GB22.2 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.InternVL2 8BShanghai AI Lab · 8.1BQ3_K_M10.0 GB11.0 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Vision 128K InstructMicrosoft · 4.2BQ4_K_M10.7 GB16.5 tok/sRuns well
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 1.5B InstructAlibaba · 1.5BQ4_K_M6.1 GB44.6 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 1.5B InstructTII · 1.6BQ4_K_M6.1 GB44.3 tok/sRuns great
36Basic quality (D) · 36 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 3 10B InstructTII · 10BQ2_K10.4 GB10.9 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 7B InstructAlibaba · 7.6BQ3_K_M9.2 GB11.6 tok/sRuns well
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 2.4BLG AI Research · 2.4BQ3_K_M6.8 GB36.8 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 15B InstructBigCode · 16BQ4_K_M15.4 GB4.3 tok/sSlow
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.DeepScaleR 1.5B PreviewAgentica · 1.8BQ4_K_M6.3 GB38.6 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)Q3_K_M13.9 GB28.7 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Command R7BCohere · 8.0BQ3_K_M9.3 GB11.0 tok/sRuns well
36Basic quality (D) · 36 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.GLM-4 9B 0414Zhipu AI · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 7B InstructAlibaba · 8.3BQ3_K_M9.5 GB10.7 tok/sRuns well
35Basic quality (D) · 35 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.Yi 1.5 34B Chat01.AI · 34BQ2_K19.7 GB3.3 tok/sSlow
36Basic quality (D) · 36 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.NorthCUA Nanobeipo-ai · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
35Basic quality (D) · 35 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.Gemma 2 9B ITGoogle · 9.2BQ2_K10.3 GB12.2 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 14B ChatAlibaba · 14BQ4_K_M20.3 GB4.8 tok/sSlow
35Basic quality (D) · 35 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.S5 nanoMaritaca AI · 4.7BQ4_K_M8.1 GB14.7 tok/sRuns well
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 2B InstructIBM · 2.5BQ3_K_M6.9 GB35.1 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 2BIBM · 2.5BQ3_K_M6.9 GB35.1 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Aya Vision 8BCohere · 8.6BQ3_K_M9.5 GB10.3 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Voxtral Mini 3BMistral AI · 4.7BQ4_K_M8.8 GB14.7 tok/sRuns well
35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4BQ3_K_M10.4 GB10.5 tok/sRuns well
35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Llama 3 8B InstructMeta · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 Llama 3.2 3BNous Research · 3.2BQ4_K_M7.8 GB21.4 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 3B InstructAlibaba · 3.8BQ4_K_M7.5 GB18.3 tok/sRuns well
22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 1.5B InstructAlibaba · 1.5BQ4_K_M6.1 GB44.6 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 1.6BLiquid AI · 1.6BQ4_K_M6.0 GB43.4 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 6.7B InstructDeepSeek · 6.7BQ4_K_M13.4 GB10.2 tok/sRuns well
20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)Q3_K_M13.6 GB29.7 tok/sRuns well
35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Command R7B ArabicCohere · 8.0BQ3_K_M9.3 GB11.0 tok/sRuns well
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 2B InstructIBM · 2.5BQ3_K_M6.9 GB35.1 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.WeVisOne VL 2BTencent · 2.4BQ3_K_M7.1 GB36.4 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)Q6_K8.2 GB49.0 tok/sRuns great
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 7B ChatShanghai AI Lab · 7.7BQ3_K_M9.8 GB11.5 tok/sRuns well
56Good quality (B) · 56 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.Mistral Large 2.1 (2411)Mistral AI · 123BQ2_K56.9 GB0.8 tok/sVery slowover memory limit
33Basic quality (D) · 33 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.GLM-4 9B Chat 1MZhipu AI · 9.5BQ2_K9.4 GB11.9 tok/sRuns well
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 2BGoogle · 2.6BQ3_K_M6.7 GB34.0 tok/sRuns great
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 8BCohere · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Apertus 8B InstructSwiss AI · 8.1BQ3_K_M10.0 GB11.0 tok/sRuns well
20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM2 2.2B InstructHugging Face · 2.3BQ3_K_M7.7 GB39.4 tok/sRuns great
21Basic quality (D) · 21 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.Llama 3.2 1B InstructMeta · 1.2BQ5_K_M6.1 GB45.7 tok/sRuns great
33Basic quality (D) · 33 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.GLM-4 9B Chat (2024)Zhipu AI · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 20B InstructIBM · 20BQ4_K_M17.4 GB3.4 tok/sSlow
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 8B InstructIBM · 8.2BQ3_K_M9.6 GB10.9 tok/sRuns well
32Basic quality (D) · 32 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.Apertus v1.5 8BSwiss AI · 8.9BQ2_K9.6 GB12.7 tok/sRuns well
33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 9B Chat01.AI · 8.8BQ3_K_M10.1 GB10.0 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 6.7B V2LLM4Binary · 6.7BQ4_K_M13.4 GB10.2 tok/sRuns well
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 1.8B InstructTencent · 1.8BQ4_K_M6.6 GB38.3 tok/sRuns great
30Basic quality (D) · 30 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.DeepSeek Coder 33B InstructDeepSeek · 33BQ2_K20.4 GB3.4 tok/sSlow
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 3B InstructTII · 3.2BQ3_K_M7.3 GB27.5 tok/sRuns well
30Basic quality (D) · 30 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.Qwen1.5 32B ChatAlibaba · 33BQ2_K20.1 GB3.5 tok/sSlow
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8BQ4_K_M6.3 GB38.6 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 1.7B InstructHugging Face · 1.7BQ4_K_M7.6 GB40.1 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 2B InstructAlibaba · 2.2BQ3_K_M6.3 GB40.1 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.3Mistral AI · 7.3BQ3_K_M9.6 GB12.2 tok/sRuns well
54Fair quality (C) · 54 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.Mistral Large 2 (123B)Mistral AI · 123BQ2_K57.1 GB0.8 tok/sVery slowover memory limit
54Fair quality (C) · 54 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.Pixtral Large 124B (2411)Mistral AI · 124BQ2_K57.5 GB0.8 tok/sVery slowover memory limit
28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 13B InstructMeta · 13BQ4_K_M19.6 GB5.3 tok/sSlow
30Basic quality (D) · 30 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.LLaVA 1.6 34BLLaVA · 35BQ2_K19.9 GB3.2 tok/sSlow
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 7B InstructZyphra · 7.4BQ3_K_M9.3 GB12.1 tok/sRuns well
32Basic quality (D) · 32 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.CodeGeeX4 All 9BZhipu AI · 9.4BQ2_K9.0 GB12.0 tok/sRuns well
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 2.2B InstructHugging Face · 2.3BQ3_K_M7.7 GB39.4 tok/sRuns great
17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)Q6_K8.0 GB49.0 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 7B InstructAi2 · 7.3BQ3_K_M10.7 GB12.2 tok/sRuns well
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 2B InstructIBM · 2.6BQ3_K_M6.6 GB33.7 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 1BGoogle · 1.0BQ6_K5.8 GB47.6 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.0 7.8B InstructLG AI Research · 7.8BQ3_K_M9.3 GB11.3 tok/sRuns well
32Basic quality (D) · 32 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.Qwen2.5-Omni 7BAlibaba · 11BQ2_K9.7 GB10.5 tok/sRuns well
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Falcon3 Mamba 7B InstructTII · 7.3BQ3_K_M8.5 GB12.2 tok/sRuns well
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 9B V2LLM4Binary · 8.8BQ3_K_M10.1 GB10.0 tok/sRuns well
19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 1.5B InstructAlibaba · 1.5BQ4_K_M6.0 GB44.6 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.SQLCoder 7B v2Defog · 6.7BQ4_K_M13.4 GB10.2 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Mistral 7BNous Research · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B BetaNexusflow · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 7BGoogle · 8.5BQ3_K_M12.9 GB10.4 tok/sRuns well
19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.d1 2BLiquid AI · 1.9BQ4_K_M6.2 GB35.7 tok/sRuns great
18Basic quality (D) · 18 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.Granite Vision 3.2 2BIBM · 3.0BQ2_K6.8 GB37.8 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (0106)OpenChat · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
18Basic quality (D) · 18 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.LFM2 700MLiquid AI · 0.7BQ8_05.8 GB47.2 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Codestral Mamba 7BMistral AI · 7.3BQ3_K_M8.6 GB12.2 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 7B InstructAlibaba · 7.6BQ3_K_M8.9 GB11.6 tok/sRuns well
29Basic quality (D) · 29 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.Llama 3.2 11B Vision InstructMeta · 11BQ2_K10.6 GB10.6 tok/sRuns well
28Basic quality (D) · 28 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.Yi 34B Chat01.AI · 34BQ2_K19.7 GB3.3 tok/sSlow
30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 9B Chat01.AI · 8.8BQ3_K_M9.7 GB10.0 tok/sRuns well
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.2Mistral AI · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mistral 7B DPONous Research · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (1210)OpenChat · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Mathstral 7BMistral AI · 7.3BQ3_K_M9.6 GB12.2 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 15B (base)BigCode · 16BQ4_K_M15.4 GB4.3 tok/sSlow
14Basic quality (D) · 14 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.Stable Code Instruct 3BStability AI · 2.8BQ2_K8.8 GB40.3 tok/sRuns great
15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 1.5B Chat01.AI · 1.5BQ4_K_M7.5 GB46.4 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Aya 23 8BCohere · 8.0BQ3_K_M10.0 GB11.0 tok/sRuns well
17Basic quality (D) · 17 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 1.8B ChatShanghai AI Lab · 1.9BQ4_K_M6.9 GB36.3 tok/sRuns great
28Basic quality (D) · 28 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.Granite Code 34B InstructIBM · 34BQ2_K18.8 GB3.3 tok/sSlow
28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Omni 3BAlibaba · 5.5BQ4_K_M8.6 GB12.4 tok/sRuns well
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 2.7B InstructZyphra · 2.7BQ3_K_M6.6 GB33.4 tok/sRuns great
26Basic quality (D) · 26 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.Code Llama 34B InstructMeta · 34BQ2_K20.1 GB3.3 tok/sSlow
15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 1B InstructTII · 1.7BQ4_K_M6.6 GB41.1 tok/sRuns great
28Basic quality (D) · 28 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.Nous Hermes 2 SOLAR 10.7BNous Research · 11BQ2_K10.0 GB10.5 tok/sRuns well
28Basic quality (D) · 28 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.SOLAR 10.7B InstructUpstage · 11BQ2_K10.0 GB10.5 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.OpenHermes 2.5 Mistral 7BTeknium · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B AlphaBerkeley · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 1.5B InstructAlibaba · 1.5BQ4_K_M6.1 GB44.6 tok/sRuns great
15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Spark X2.6 1.7BSparkLLM · 1.7BQ4_K_M6.1 GB40.1 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 13BMicrosoft · 13BQ4_K_M16.2 GB5.3 tok/sSlow
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 7BShanghai AI Lab · 7.7BQ3_K_M9.8 GB11.5 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 8B Instruct (128K)IBM · 8.1BQ3_K_M10.1 GB11.0 tok/sRuns well
16Basic quality (D) · 16 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 2BFastino · 1.9BQ4_K_M6.2 GB36.5 tok/sRuns great
15Basic quality (D) · 15 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.surya ocr 2.5Datalab · 0.7BQ8_05.8 GB50.6 tok/sRuns great
14Basic quality (D) · 14 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.Qwen3 0.6BAlibaba · 0.8BQ8_06.7 GB46.6 tok/sRuns great
14Basic quality (D) · 14 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.LFM2.5 350MLiquid AI · 0.4BF165.8 GB46.0 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 6B Chat01.AI · 6.1BQ4_K_M8.9 GB11.3 tok/sRuns well
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.1Mistral AI · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 1.7B InstructHugging Face · 1.7BQ4_K_M6.4 GB40.1 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 0.5B InstructTII · 0.5BQ8_05.7 GB67.2 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Gemma 1.1 7B ITGoogle · 8.5BQ3_K_M12.9 GB10.4 tok/sRuns well
13Basic quality (D) · 13 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 1B InstructAi2 · 1.5BQ4_K_M6.4 GB46.4 tok/sRuns great
14Basic quality (D) · 14 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.Granite Code 3B Instruct (128K)IBM · 3.5BQ2_K9.0 GB32.4 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Baichuan 2 13B ChatBaichuan · 14BQ4_K_M16.8 GB4.9 tok/sSlow
22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 7B InstructMeta · 6.7BQ4_K_M13.4 GB10.2 tok/sRuns well
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 13B ChatMeta · 13BQ4_K_M16.2 GB5.3 tok/sSlow
11Basic quality (D) · 11 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.DeepSeek Coder 1.3B InstructDeepSeek · 1.4BQ5_K_M7.5 GB42.0 tok/sRuns great
11Basic quality (D) · 11 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.LLM4Decompile 1.3B V2LLM4Binary · 1.4BQ5_K_M7.5 GB42.0 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 7B ChatAlibaba · 7.7BQ3_K_M13.0 GB11.5 tok/sRuns well
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Falcon Mamba 7B InstructTII · 7.3BQ3_K_M8.5 GB12.2 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 12B ChatStability AI · 12BQ4_K_M13.2 GB5.7 tok/sSlow
11Basic quality (D) · 11 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.StableLM Zephyr 3BStability AI · 2.8BQ2_K7.4 GB40.3 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Neural Chat 7B v3.3Intel · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Gemma 7B ITGoogle · 8.5BQ3_K_M12.9 GB10.4 tok/sRuns well
15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Falcon 40B InstructTII · 42BQ4_K_M30.7 GB1.6 tok/sVery slow
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Phi-2 2.7BMicrosoft · 2.8BQ2_K6.7 GB40.5 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 3BBigCode · 3.0BQ2_K6.4 GB37.2 tok/sRuns great
12Basic quality (D) · 12 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 350MLiquid AI · 0.4BF165.8 GB46.0 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 Mistral 7BLLaVA · 7.6BQ3_K_M9.7 GB11.7 tok/sRuns well
12Basic quality (D) · 12 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.Granite 4.0 H 350MIBM · 0.3BF165.7 GB47.4 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 450MLiquid AI · 0.5BQ8_05.5 GB77.6 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.RecurrentGemma 9B ITGoogle · 9.6BQ2_K8.9 GB11.7 tok/sRuns well
11Basic quality (D) · 11 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 0.8BFastino · 0.8BQ8_05.8 GB46.6 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.StarCoder 15BBigCode · 16BQ4_K_M14.8 GB4.3 tok/sSlow
15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Mini 4B InstructNVIDIA · 4.2BQ2_K7.2 GB26.9 tok/sRuns well
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.WizardMath 7B v1.1WizardLM · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Zephyr 7B BetaHugging Face · 7.2BQ3_K_M9.6 GB12.3 tok/sRuns well
9Basic quality (D) · 9 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 1.6B ChatStability AI · 1.6BQ4_K_M6.8 GB41.8 tok/sRuns great
9Basic quality (D) · 9 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 Zephyr 1.6BStability AI · 1.6BQ4_K_M6.8 GB41.8 tok/sRuns great
9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 2BGoogle · 2.5BQ2_K6.1 GB44.9 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 500M InstructHugging Face · 0.5BQ8_05.8 GB68.5 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 0.5B InstructAlibaba · 0.5BQ8_05.6 GB71.3 tok/sRuns great
10Basic quality (D) · 10 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.LFM2.5 230MLiquid AI · 0.2BF165.5 GB70.0 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 13BLLaVA · 13BQ4_K_M16.5 GB5.1 tok/sSlow
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.WizardLM 13B v1.2WizardLM · 13BQ4_K_M16.2 GB5.3 tok/sSlow
20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 7BMicrosoft · 6.7BQ4_K_M11.2 GB10.2 tok/sRuns well
8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2B ITGoogle · 2.5BQ2_K6.1 GB44.9 tok/sRuns great
8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 0.5B InstructTencent · 0.5BQ8_06.3 GB64.7 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.StarCoder2 7BBigCode · 7.2BQ3_K_M9.0 GB12.4 tok/sRuns well
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 · 0.4BF166.0 GB44.7 tok/sRuns great
8Basic quality (D) · 8 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 0.5B InstructAlibaba · 0.5BQ8_05.6 GB71.3 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Vicuna 13B v1.5LMSYS · 13BQ4_K_M16.2 GB5.3 tok/sSlow
16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 7B ChatMeta · 6.7BQ3_K_M10.4 GB13.2 tok/sRuns well
16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Baichuan 2 7B ChatBaichuan · 7.5BQ3_K_M10.8 GB11.8 tok/sRuns well
5Basic quality (D) · 5 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.TinyLlama 1.1B ChatTinyLlama · 1.1BQ6_K5.9 GB43.3 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 · 0.4BF165.8 GB44.7 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Yi 6B Chat01.AI · 6.1BQ3_K_M8.2 GB14.6 tok/sRuns well
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 · 0.3BF165.7 GB61.9 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 0.5B InstructAlibaba · 0.5BQ8_05.6 GB71.3 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 · 0.3BF165.5 GB59.6 tok/sRuns great
15Basic quality (D) · 15 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek LLM 7B ChatDeepSeek · 6.9BQ3_K_M10.4 GB12.8 tok/sRuns well
5Basic quality (D) · 5 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.SmolLM 360M InstructHugging Face · 0.4BF165.8 GB44.7 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 · 0.1BF165.4 GB124 tok/sRuns great
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 7BLLaVA · 7.1BQ2_K9.9 GB16.0 tok/sRuns well
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 · 0.1BF165.2 GB179 tok/sRuns great
9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.Vicuna 7B v1.5LMSYS · 6.7BQ2_K9.8 GB16.7 tok/sRuns well
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 · 0.1BF165.3 GB124 tok/sRuns great
9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.OLMo 7B InstructAi2 · 6.9BQ2_K8.8 GB16.4 tok/sRuns well
8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking.InternLM 7BShanghai AI Lab · 7.3BQ2_K9.0 GB15.4 tok/sRuns well
4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking.Falcon 7B InstructTII · 7.2BQ2_K7.9 GB15.6 tok/sRuns well
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)MXFP471.8 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_K1,117 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_K310 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_K307 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_K984 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_K1,117 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_K415 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_K234 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_K178 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_K247 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_K134 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_K130 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_K310 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_K427 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_K77.2 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_K307 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_K318 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_K334 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_K666 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_K416 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_K234 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_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.Intern-S2 (397B-A17B)Shanghai AI Lab · 403B (17.0B active)Q2_K167 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_K307 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_K164 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_K645 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_K129 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_K167 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_K177 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_K307 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_K159 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_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.Beam 1.0 (501B-A23B)Reflection AI · 501B (23.4B active)Q2_K206 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_K416 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_K416 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_K127 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_K130 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_K167 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_K280 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_K112 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_K151 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_K386 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_K98.5 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_K85.9 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_K229 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_K279 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_K416 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_K280 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_K415 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_K98.5 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_K274 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_K122 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_K85.1 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_K279 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_K279 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_K416 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_K98.5 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_K101 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_K199 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_K129 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_K408 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_K276 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_K101 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_K107 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_K416 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_K98.5 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_K101 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_K92.7 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.K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active)Q2_K100 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_K230 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_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.InternVL3.5 241B-A28BShanghai AI Lab · 241B (28.0B active)Q2_K103 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_K111 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_K101 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_K151 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_K279 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_K188 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_K151 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_K188 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_K59.0 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_K165 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_K127 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_K172 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_K164 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_K70.4 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_K188 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_K172 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_K274 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_K99.8 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_K99.8 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_K99.8 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_K172 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_K167 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_K99.8 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.Jamba 1.5 LargeAI21 Labs · 399B (94.0B active)Q2_K165 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_K99.8 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_K63.1 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_K133 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_K197 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_K77.1 GB—Won't run

Image models on the Intel Xeon Silver (4100 to 4300 series) NAS (64 GB)

Quality Model Quant Memory Speed Runs
92Excellent quality (A+) · 92 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.Krea 2 TurboKrea · 12.8BFP1637.4 GB3.5 minVery slow
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 9BBlack Forest Labs · 9.1BFP1637.1 GB89 sSlow
92Excellent quality (A+) · 92 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2.1Alibaba · 7.1BQ8 GGUF41.6 GB56.7 minVery slow
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2512Alibaba · 20.4BQ8 GGUF36.5 GB85.1 minVery slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-ImageBaidu · 8.0BFP1634.0 GB18.1 minVery slow
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Fibo 2.0 DevBria AI · 8.1BFP1627.7 GB18.5 minVery slow
88Excellent quality (A+) · 88 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.Qwen-Image 2.1 TurboAlibaba · 7.1BQ8 GGUF31.3 GB11.0 minVery slow
90Excellent quality (A+) · 90 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.Ideogram 4Ideogram · 18.6BFP829.9 GB18.5 minVery slow
84Great quality (A) · 84 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.Ming-Image 0.1 DesignAnt Group (inclusionAI) · 6.2BFP839.2 GB12.1 minVery slow
86Excellent quality (A+) · 86 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.Qwen-ImageAlibaba · 20.4BFP835.1 GB66.6 minVery slow
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Krea [dev]Black Forest Labs · 11.9BFP1636.4 GB9.9 minVery slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.FireRed-Image-Edit 1.1rednote (FireRed Team) · 20.4BQ8 GGUF33.9 GB75.6 minVery slow
85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image-Edit 2511Alibaba · 20.4BQ8 GGUF33.9 GB75.6 minVery slow
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Kontext [dev]Black Forest Labs · 11.9BFP1637.0 GB18.1 minVery slow
91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.FLUX 3 Image KleinBlack Forest Labs · 5.6BFP1622.4 GB4.7 minVery slow
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-Image TurboBaidu · 8.0BFP1626.4 GB2.6 minVery slow
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FullHiDream.ai · 17.1BQ8 GGUF34.9 GB42.5 minVery slow
80Great quality (A) · 80 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.FLUX.1 [dev]Black Forest Labs · 11.9BFP1636.4 GB9.9 minVery slow
85Excellent quality (A+) · 85 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.FLUX.2 [dev]Black Forest Labs · 32.2BQ4 GGUF46.8 GB35.5 minVery slowtight fit
79Great quality (A) · 79 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 DevHiDream.ai · 17.1BQ8 GGUF34.9 GB16.1 minVery slow
84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Z-Image TurboAlibaba (Tongyi) · 6.2BFP1622.7 GB2.1 minSlow
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [schnell]Black Forest Labs · 11.9BFP1636.4 GB1.6 minSlow
82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.MOSS-Image SFTOpenMOSS · 5.1BFP1629.3 GB11.5 minVery slow
76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Fill [dev]Black Forest Labs · 11.9BFP1636.4 GB10.3 minVery slow
75Great quality (A) · 75 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FastHiDream.ai · 17.1BQ8 GGUF34.9 GB9.5 minVery slow
78Great quality (A) · 78 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.FLUX.2 [klein] 4BBlack Forest Labs · 3.9BFP1618.1 GB49 sSlow
78Great quality (A) · 78 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.Chroma1-HDLodestone Rock · 8.9BFP1630.0 GB16.4 minVery slow
82Great quality (A) · 82 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.Z-ImageAlibaba (Tongyi) · 6.2BFP1622.7 GB14.0 minVery slow
70Great quality (A) · 70 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.CogView4 6BZhipu AI · 6.4BFP1633.9 GB14.8 minVery slow
62Good quality (B) · 62 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.Stable Diffusion 3.5 Large TurboStability AI · 8.1BFP1630.0 GB79 sSlow
66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 LargeStability AI · 8.1BFP1630.0 GB9.0 minVery slow
72Great quality (A) · 72 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.Iris-3BSperidlabs · 3.0BFP1617.3 GB13.2 minVery slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.HunyuanImage 3.0 (80B-A13B)Tencent · 83.0BFP832.8 GB57.7 minVery slowCPU offload
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Cosmos3-Super Text2Image (64B)NVIDIA · 64.0BFP826.1 GB38.5 minVery slowCPU offload
66Good quality (B) · 66 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.OmniGen2BAAI (VectorSpaceLab) · 4.0BFP1618.0 GB13.2 minVery slow
60Good quality (B) · 60 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.KolorsKuaishou · 2.6BFP1619.8 GB3.3 minVery slow
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 MediumStability AI · 2.5BFP1618.4 GB4.9 minVery slow
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.SDXL TurboStability AI · 2.6BFP167.6 GB7.4 sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.SDXL-Lightning (4-step)ByteDance · 2.6BFP168.9 GB35 sRuns well
62Good quality (B) · 62 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.Lumina-Image 2.0Shanghai AI Lab · 2.6BFP1612.7 GB5.8 minVery slow
58Good quality (B) · 58 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 XL v2 TurboLykon · 2.6BFP168.9 GB64 sSlow
58Good quality (B) · 58 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.AuraFlow v0.3fal · 6.9BFP1618.5 GB11.5 minVery slow
62Good quality (B) · 62 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.Juggernaut XL v9RunDiffusion · 2.6BFP168.9 GB3.7 minVery slow
62Good quality (B) · 62 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.RealVisXL V5.0SG161222 · 2.6BFP168.9 GB3.7 minVery slow
48Fair quality (C) · 48 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.Kandinsky 3Sber AI · 3.0BFP1625.9 GB7.4 minVery slow
52Fair quality (C) · 52 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.Stable Diffusion 3 MediumStability AI · 2.0BFP1617.4 GB2.5 minVery slow
60Good quality (B) · 60 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.Animagine XL 4.0Cagliostro Lab · 2.6BFP168.9 GB3.5 minVery slow
60Good quality (B) · 60 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.Illustrious XL v0.1OnomaAI · 2.6BFP168.9 GB3.5 minVery slow
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.PixArt-Σ XL 1024PixArt · 0.6BFP1612.8 GB74 sSlow
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Pony Diffusion V6 XLPurpleSmartAI · 2.6BFP168.9 GB3.1 minVery slow
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Playground v2.5Playground AI · 2.6BFP168.9 GB6.2 minVery slow
52Fair quality (C) · 52 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 CascadeStability AI · 5.2BFP1614.0 GB4.1 minVery slow
56Good quality (B) · 56 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.Animagine XL 3.1Cagliostro Lab · 2.6BFP168.9 GB3.5 minVery slow
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion XL 1.0Stability AI · 2.6BFP168.9 GB3.7 minVery slow
52Fair quality (C) · 52 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.Hunyuan-DiT v1.2Tencent · 1.5BFP169.3 GB4.9 minVery slow
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.SD TurboStability AI · 0.9BFP163.3 GB3.9 sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.LCM DreamShaper v7Tsinghua (LCM) · 0.9BFP162.8 GB12 sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Realistic Vision V5.1SG161222 · 0.9BFP162.8 GB59 sSlow
40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.DreamShaper 8Lykon · 0.9BFP162.8 GB59 sSlow
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 1.5Stability AI / Runway · 0.9BFP162.8 GB59 sSlow

Video models on the Intel Xeon Silver (4100 to 4300 series) NAS (64 GB)

Quality Model Quant Memory Speed Runs
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.LTX-2.5 (22B, video + audio)Lightricks · 21.0BQ8 GGUF49.8 GB86.0 minVery slowtight fit
85Excellent quality (A+) · 85 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.LTX-2.3Lightricks · 18.9BQ8 GGUF45.6 GB6.3 hVery slow
85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Bernini-R A14B (video generation + editing)ByteDance · 14.3BFP1646.0 GB9.9 hVery slow
85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 I2V A14BAlibaba · 14.0BQ8 GGUF39.3 GB25.2 hVery slow
85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 T2V A14BAlibaba · 14.0BQ8 GGUF39.3 GB25.2 hVery slow
81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.LTX-2 (19B, video + audio)Lightricks · 18.9BQ8 GGUF45.6 GB6.3 hVery slow
82Great quality (A) · 82 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.HunyuanVideo 1.5 (8.3B)Tencent · 8.3BFP838.4 GB22.2 hVery slow
89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.MiniMax H3 (33B, video + audio)MiniMax · 20.1BQ8 GGUF42.4 GB17.2 hVery slowencoder unloaded after use
76Great quality (A) · 76 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.HY-OmniWeaving (8.3B, unified video)Tencent · 8.3BFP1641.9 GB7.3 hVery slow
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 Animate 14BAlibaba · 17.3BQ8 GGUF42.7 GB29.9 hVery slow
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 720PAlibaba · 14.0BQ8 GGUF39.9 GB31.5 hVery slow
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 T2V 14BAlibaba · 14.0BQ8 GGUF39.3 GB31.5 hVery slow
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 VACE 14BAlibaba · 17.3BQ8 GGUF42.8 GB34.7 hVery slow
76Great quality (A) · 76 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.SkyReels V2 T2V 14B 720PSkywork · 14.0BFP841.1 GB29.6 hVery slow
78Great quality (A) · 78 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.SCAIL-2 14B (character animation)Zhipu AI · 16.4BFP829.8 GB14.8 hVery slow
70Great quality (A) · 70 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 2.2 TI2V 5BAlibaba · 5.0BFP1643.1 GB7.1 hVery slow
71Great quality (A) · 71 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo 13BTencent · 13.0BQ8 GGUF44.6 GB37.8 hVery slow
71Great quality (A) · 71 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo I2V 13BTencent · 13.0BQ8 GGUF44.6 GB37.8 hVery slow
75Great quality (A) · 75 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3BQ8 GGUF29.3 GB15.8 hVery slow
74Great quality (A) · 74 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.Step-Video T2V (30B)StepFun · 30.0BFP846.8 GB38.2 hVery slowtight fit
70Great quality (A) · 70 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.Open-Sora 2.0 (11B)HPC-AI Tech · 11.0BFP1643.8 GB41.1 hVery slow
66Good quality (B) · 66 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.LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0BFP830.1 GB44.4 minVery slow
68Good quality (B) · 68 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.Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0BFP838.8 GB19.7 hVery slow
72Great quality (A) · 72 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.FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9BFP828.2 GB4.9 hVery slow
72Great quality (A) · 72 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.SkyReels V2 T2V 14B 540PSkywork · 14.0BFP829.3 GB17.3 hVery slow
68Good quality (B) · 68 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.Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI · 3.2BFP1631.5 GB4.2 hVery slow
73Great quality (A) · 73 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 480PAlibaba · 14.0BQ8 GGUF27.2 GB14.2 hVery slow
62Good quality (B) · 62 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.Mochi 1 Preview (10B)Genmo · 10.0BFP1641.4 GB15.1 hVery slow
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.CogVideoX 1.5 5BZhipu AI · 5.6BFP840.0 GB11.1 hVery slow
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0BFP1633.6 GB3.4 hVery slow
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Wan-Dancer 14B (music to dance)Alibaba · 17.3BFP847.1 GB57.0 hVery slowtight fit · encoder unloaded after use
60Good quality (B) · 60 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.Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0BFP1648.2 GB7.5 hVery slowtight fit
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Allegro (2.8B)Rhymes AI · 2.8BFP1638.2 GB16.4 hVery slow
88Excellent quality (A+) · 88 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.Kandinsky 6.0 Pro (29B, video + audio)Sber AI · 30.1BFP1627.8 GB52.4 hVery slowCPU offload
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5B I2VZhipu AI · 5.6BFP1625.3 GB2.5 hVery slow
55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5BZhipu AI · 5.0BFP1624.1 GB2.5 hVery slow
55Good quality (B) · 55 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.Wan 2.1 VACE 1.3BAlibaba · 2.2BFP1621.5 GB3.6 hVery slow
50Fair quality (C) · 50 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.LTX-Video 2BLightricks · 1.9BFP1617.5 GB20.5 minSlow
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.SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4BFP1623.8 GB4.1 hVery slow
55Good quality (B) · 55 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.Wan 2.1 T2V 1.3BAlibaba · 1.3BFP1619.8 GB3.3 hVery slow
45Fair quality (C) · 45 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 2BZhipu AI · 1.7BFP1617.5 GB49.3 minVery slow
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3BFP164.7 GB16.4 minSlow
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

Decision models on the Intel Xeon Silver (4100 to 4300 series) NAS (64 GB)

Quality Model Quant Memory Speed Runs
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 GB50 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 22MMeta · 71MQ8_00.7 GB117 msRuns great
86Excellent quality (A+) · 86 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.Jina Reranker v3.5Jina AI · 600MQ8_05.8 GB899 msSlow
80Great quality (A) · 80 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.GLiNER2.5 DecideFastino · 490MQ8_01.2 GB394 msRuns well
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v3Jina AI · 600MQ8_05.8 GB899 msSlow
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 4BAlibaba · 4.0BQ8_09.5 GB6.0 sVery slow
90Excellent quality (A+) · 90 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.Qwen3 Reranker 8BAlibaba · 8.2BQ8_013.9 GB12.2 sVery slow
80Great quality (A) · 80 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.FRIDA-DecisionsSber AI · 820MQ8_01.7 GB656 msSlow
66Good quality (B) · 66 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.GLiClass Base v3Knowledgator · 190MQ8_00.8 GB155 msRuns well
74Great quality (A) · 74 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.GLiClass ModernBERT Large v3Knowledgator · 400MQ8_01.1 GB322 msRuns well
88Excellent quality (A+) · 88 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.zerank-2ZeroEntropy · 4.0BQ8_09.5 GB6.0 sVery slow
90Excellent quality (A+) · 90 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.Skywork Reward V2 Llama 3.1 8BSkywork · 7.5BQ8_010.4 GB23.9 sVery slow
76Great quality (A) · 76 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.Llama Prompt Guard 2 86MMeta · 280MQ8_01.0 GB449 msSlow
64Good quality (B) · 64 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.DeBERTa v3 Base Zero-shot v2.0Moritz Laurer · 180MQ8_00.8 GB147 msRuns well
70Great quality (A) · 70 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.GTE Reranker ModernBERT BaseAlibaba · 150MQ8_00.8 GB243 msRuns well
80Great quality (A) · 80 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.Qwen3 Reranker 0.6BAlibaba · 600MQ8_05.8 GB899 msSlow
86Excellent quality (A+) · 86 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.Shieldstral 1.0 3BMistral AI · 3.9BQ8_09.3 GB5.7 sVery slow
72Great quality (A) · 72 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.DeBERTa v3 Large Zero-shot v2.0Moritz Laurer · 440MQ8_01.2 GB354 msRuns well
84Great quality (A) · 84 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.Intern-Decision 4BShanghai AI Lab · 4.5BQ8_09.8 GB3.5 sVery slow
68Good quality (B) · 68 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.Granite Embedding Reranker English R2IBM · 150MQ8_00.8 GB243 msRuns well
68Good quality (B) · 68 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.GLiNER2 Base v1Fastino · 210MQ8_00.9 GB171 msRuns well
82Great quality (A) · 82 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.mxbai-rerank-large v2Mixedbread · 1.5BQ8_06.6 GB2.3 sVery slow
82Great quality (A) · 82 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.d1 3BLiquid AI · 3.1BQ8_08.3 GB2.4 sVery slow
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.ModernBERT Large Zero-shot v2.0Moritz Laurer · 400MQ8_01.1 GB322 msRuns well
86Excellent quality (A+) · 86 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.GLiDE 27BFastino · 26BQ8_034.8 GB20.7 sVery slow
76Great quality (A) · 76 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.mxbai-rerank-base v2Mixedbread · 490MQ8_05.5 GB735 msSlow
80Great quality (A) · 80 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.zerank-1 smallZeroEntropy · 1.7BQ8_07.0 GB2.6 sVery slow
84Great quality (A) · 84 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.Skywork Reward V2 Qwen3 8BSkywork · 7.6BQ8_010.5 GB24.1 sVery slow
68Good quality (B) · 68 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.GLiGuard 300MFastino · 210MQ8_00.9 GB338 msRuns well
68Good quality (B) · 68 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.LayaConvai Innovations · 420MQ8_01.2 GB338 msRuns well
70Great quality (A) · 70 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.Jina Reranker v2 Base MultilingualJina AI · 280MQ8_01.0 GB449 msSlow
66Good quality (B) · 66 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.ProtectAI DeBERTa v3 Prompt Injection v2Protect AI · 180MQ8_00.8 GB290 msRuns well
80Great quality (A) · 80 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.LemonDecider 4BAnt Group (inclusionAI) · 4.5BQ8_06.5 GB3.6 sVery slow
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 GB46 msRuns great
72Great quality (A) · 72 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.DuoGuard 0.5BDuoGuard · 490MQ8_01.2 GB783 msSlow
78Great quality (A) · 78 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.BGE Reranker v2 GemmaBAAI · 2.5BQ8_07.7 GB3.7 sVery slow
72Great quality (A) · 72 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.BGE Reranker v2 M3BAAI · 570MQ8_01.3 GB910 msSlow
86Excellent quality (A+) · 86 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.Qwen3Guard Gen 8BAlibaba · 8.2BQ8_013.9 GB13.4 sVery slow
84Great quality (A) · 84 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.Qwen3Guard Gen 4BAlibaba · 4.4BQ8_09.9 GB7.2 sVery slow
60Good quality (B) · 60 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.Laya MultilingualConvai Innovations · 320MQ8_01.0 GB258 msRuns well
84Great quality (A) · 84 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.Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 8.0BQ8_013.7 GB13.1 sVery slow
84Great quality (A) · 84 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.Granite Guardian 4.1 8BIBM · 8.4BQ8_014.2 GB13.7 sVery slow
62Good quality (B) · 62 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.HHEM 2.1 OpenVectara · 110MQ8_00.7 GB354 msRuns well
72Great quality (A) · 72 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.Skywork Reward V2 Qwen3 0.6BSkywork · 600MQ8_01.4 GB1.9 sVery slow
62Good quality (B) · 62 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.GLiNER Multi v2.1Urchade Zaratiana · 290MQ8_01.0 GB235 msRuns well
74Great quality (A) · 74 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.Qwen3Guard Gen 0.6BAlibaba · 750MQ8_06.0 GB1.2 sSlow
80Great quality (A) · 80 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.WildGuard 7BAi2 · 7.3BQ8_012.9 GB11.9 sVery slow
80Great quality (A) · 80 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.Granite Guardian 3.3 8BIBM · 8.2BQ8_013.9 GB13.4 sVery slow
76Great quality (A) · 76 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.NuExtract 2.0 4BNuMind · 3.8BQ8_09.0 GB5.3 sVery slow
56Good quality (B) · 56 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.BART Large MNLIMeta · 410MQ8_01.1 GB330 msRuns well
86Excellent quality (A+) · 86 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.CompassJudger-2 32BOpenCompass · 33BQ8_040.2 GB236.5 sVery slow
70Great quality (A) · 70 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.NuExtract 2.0 2BNuMind · 2.2BQ8_07.4 GB3.1 sVery slow
66Good quality (B) · 66 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.LettuceDetect LargeKR Labs · 400MQ8_01.1 GB1.3 sSlow
79Great quality (A) · 79 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.DynaGuard 8BUniversity of Maryland · 8.2BQ8_013.9 GB49.5 sVery slow
78Great quality (A) · 78 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.Nemotron Content Safety Reasoning 4BNVIDIA · 4.3BQ8_09.8 GB26.0 sVery slow
80Great quality (A) · 80 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.Selene 1 Mini 8BAtla · 8.0BQ8_013.7 GB58.0 sVery slow
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 20BOpenAI · 22B (3.6B active)MXFP417.3 GB13.7 sVery slow
66Good quality (B) · 66 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.ShieldGemma 27BGoogle · 27BQ8_034.6 GB40.6 sVery slow
64Good quality (B) · 64 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.ShieldGemma 9BGoogle · 9.2BQ8_015.5 GB13.8 sVery slow
78Great quality (A) · 78 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.CompassJudger-2 7BOpenCompass · 7.6BQ8_013.1 GB55.0 sVery slow
68Good quality (B) · 68 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.Llama Guard 3 8BMeta · 8.0BQ8_013.7 GB13.1 sVery slow
58Good quality (B) · 58 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.ShieldGemma 2BGoogle · 2.6BQ8_07.9 GB3.9 sVery slow
70Great quality (A) · 70 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.DynaGuard 1.7BUniversity of Maryland · 2.0BQ8_07.3 GB12.3 sVery slow
66Good quality (B) · 66 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.Llama Guard 4 12BMeta · 12BQ8_018.1 GB19.6 sVery slow
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Prometheus 2 8x7BPrometheus Eval · 47B (13B active)Q6_K43.5 GB78.9 sVery slow
68Good quality (B) · 68 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.Prometheus 2 7BPrometheus Eval · 7.2BQ8_012.9 GB52.3 sVery slow
56Good quality (B) · 56 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.Llama Guard 3 1BMeta · 1.5BQ8_06.6 GB2.5 sVery slow
66Good quality (B) · 66 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.GLIDERPatronus AI · 3.8BQ8_09.8 GB27.6 sVery slow
64Good quality (B) · 64 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.Flow Judge v0.1Flow AI · 3.8BQ8_09.8 GB27.6 sVery slow
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)MXFP471.6 GB—Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 358 of 619 LLMs run well on your Intel Xeon Silver (4100 to 4300 series) NAS (64 GB).

ASRock Intel Arc B570 Challenger 10GB OC Cheapest upgrade Intel Arc B570 10.0 GB · $219 launch price +26 LLMs run well, including Qwen3.8 27B
AMD Radeon RX 7600 XT Best value AMD Radeon RX 7600 XT 16.0 GB · $329 launch price +98 LLMs run well, including Nanbeige4.3 33B
NVIDIA RTX PRO 6000 Blackwell Workstation Edition Biggest jump NVIDIA RTX PRO 6000 Blackwell 96.0 GB · $8,565 launch price +188 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?