What the AMD EPYC 7002 / 7003 series NAS (16 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
16.0 GB
Usable for models
12.0 GB
Memory bandwidth
205 GB/s
FP16 compute
1.0 TFLOPS
396 / 619 LLMs run Best: Mellum2.1 Thinking (12B-A2.5B) (B) 54 / 60 Image models run Best: FLUX.2 [klein] 4B (A) 14 / 43 Video models run Best: LTX-Video 2B (C) 65 / 70 Decision models run Best: OpenAI Privacy Filter (A)

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

LLMs on the AMD EPYC 7002 / 7003 series NAS (16 GB)

Quality Model Quant Memory Speed Runs
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Mellum2.1 Thinking (12B-A2.5B)JetBrains · 12B (2.5B active)Q4_K_M9.1 GB47.0 tok/sRuns great
78Great quality (A) · 78 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.Gemma 4 12BGoogle · 12BQ4_K_M9.5 GB11.7 tok/sRuns well
76Great quality (A) · 76 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.K2 Horizon 7BInstitute of Foundation Models · 9.0BQ4_K_M8.3 GB15.5 tok/sRuns well
74Great quality (A) · 74 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.SenseNova Loop 9B PreviewSenseTime · 9.7BQ4_K_M7.9 GB14.5 tok/sRuns well
74Great quality (A) · 74 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.MiMo V2.6 Distill Qwen 9BXiaomi · 9.4BQ4_K_M7.6 GB14.8 tok/sRuns well
60Good quality (B) · 60 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.Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)Q8_010.1 GB45.3 tok/sRuns great
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 9BDeepReinforce · 9.7BQ4_K_M7.7 GB14.5 tok/sRuns well
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 9BAlibaba · 9.7BQ4_K_M7.7 GB14.5 tok/sRuns well
71Great quality (A) · 71 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.Ornith 1.0 9BDeepReinforce · 9.7BQ4_K_M7.7 GB14.5 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Bolt E4BNVIDIA · 8.0BQ4_K_M6.6 GB31.0 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Maple Preview (20B-A1B)DeepGrove · 20B (1.5B active)Q3_K_M11.6 GB87.0 tok/sRuns welltight fit
70Great quality (A) · 70 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.TMax 9BAi2 · 9.0BQ4_K_M7.3 GB15.6 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 E4BGoogle · 8.0BQ4_K_M6.6 GB31.0 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)Q4_K_M11.8 GB40.2 tok/sRuns welltight fit
61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 E2BGoogle · 5.1BQ6_K5.8 GB42.1 tok/sRuns great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.UI-Mate 9BTencent · 9.4BQ4_K_M7.6 GB14.8 tok/sRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.UI-Venus 2 9BAnt Group (inclusionAI) · 9.4BQ4_K_M7.6 GB14.8 tok/sRuns well
64Good quality (B) · 64 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.Nanbeige4.2 3BBOSS Zhipin (Nanbeige) · 4.2BQ4_K_M5.6 GB33.5 tok/sRuns great
64Good quality (B) · 64 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.Granite 4.2 8BIBM · 8.8BQ4_K_M8.3 GB15.9 tok/sRuns well
51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)Q6_K8.6 GB52.4 tok/sRuns great
51Fair quality (C) · 51 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.LFM2.5 24B-A2BLiquid AI · 24B (2.5B active)Q2_K11.3 GB72.4 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 76/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Labs Dory 1.0 4BNVIDIA · 4.0BQ4_K_M4.5 GB35.1 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)Q4_K_M11.4 GB48.7 tok/sRuns welltight fit
49Fair quality (C) · 49 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.Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)Q4_K_M11.8 GB74.7 tok/sRuns welltight fit
58Good quality (B) · 58 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.DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2BQ4_K_M7.8 GB17.1 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 8BShanghai AI Lab · 8.5BQ4_K_M8.0 GB16.4 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)Q2_K10.8 GB61.7 tok/sRuns welltight fit
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 8B InstructAlibaba · 8.8BQ4_K_M8.1 GB15.9 tok/sRuns well
47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Groot 19B A3B 261023GrootTeam · 19B (3.0B active)Q3_K_M11.2 GB50.4 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 75/100 (quality, fit, speed and memory use) sets the ranking.Spark-X2.6 4BSparkLLM · 4.1BQ4_K_M4.4 GB34.0 tok/sRuns great
47Fair quality (C) · 47 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-VL A3B InstructMoonshot AI · 16B (3.0B active)Q4_K_M11.8 GB40.2 tok/sRuns welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 8BAlibaba · 8.2BQ4_K_M7.8 GB17.1 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.5 8BOpenBMB · 8.7BQ4_K_M8.1 GB16.1 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 8BIBM · 8.8BQ4_K_M8.3 GB15.9 tok/sRuns well
44Fair quality (C) · 44 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 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)Q8_09.0 GB56.0 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Unlimited OCR 2 (3B-A0.6B)Baidu · 3.3B (0.6B active)F168.7 GB44.1 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 14B ReasoningMistral AI · 14BQ4_K_M11.4 GB10.0 tok/sRuns welltight fit
60Good quality (B) · 60 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.Phi-4 Reasoning Plus (14B)Microsoft · 15BQ3_K_M10.4 GB12.3 tok/sRuns welltight fit
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.MiMo-VL 7B RLXiaomi · 8.3BQ4_K_M7.8 GB16.8 tok/sRuns well
60Good quality (B) · 60 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.Apriel 1.5 15B ThinkerServiceNow · 15BQ3_K_M10.5 GB12.2 tok/sRuns welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL-Cowork 4.7BMicrosoft · 4.7BQ4_K_M5.7 GB29.5 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.1V 9B ThinkingZhipu AI · 10BQ4_K_M8.2 GB13.6 tok/sRuns well
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Seed-Coder 8B ReasoningByteDance · 8.3BQ4_K_M7.7 GB16.9 tok/sRuns well
44Fair quality (C) · 44 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.ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)Q2_K10.8 GB61.7 tok/sRuns welltight fit
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 2BOpenBMB · 2.5BQ6_K4.0 GB38.5 tok/sRuns great
57Good quality (B) · 57 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 14BAlibaba · 15BQ3_K_M10.2 GB12.2 tok/sRuns well
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 14BMistral AI · 14BQ4_K_M11.4 GB10.0 tok/sRuns welltight fit
58Good quality (B) · 58 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.Phi-4 Reasoning (14B)Microsoft · 15BQ3_K_M10.4 GB12.3 tok/sRuns welltight fit
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Nano 9B v2NVIDIA · 8.9BQ4_K_M7.1 GB15.7 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 12B ITGoogle · 12BQ4_K_M9.7 GB11.4 tok/sRuns well
43Fair quality (C) · 43 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.Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)Q4_K_M11.6 GB40.2 tok/sRuns welltight fit
58Good quality (B) · 58 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.Phi-4 Reasoning Vision 15BMicrosoft · 15BQ3_K_M10.6 GB11.9 tok/sRuns welltight fit
55Good quality (B) · 55 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.GLM-Z1 9B (0414)Zhipu AI · 9.4BQ4_K_M7.6 GB14.9 tok/sRuns well
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 4BAlibaba · 4.7BQ4_K_M4.7 GB30.0 tok/sRuns well
53Fair quality (C) · 53 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.MiMo 7B RLXiaomi · 7.8BQ4_K_M7.5 GB17.8 tok/sRuns well
53Fair quality (C) · 53 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.Seed-Coder 8B InstructByteDance · 8.3BQ4_K_M7.7 GB16.9 tok/sRuns well
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 8BMistral AI · 8.9BQ4_K_M8.1 GB15.7 tok/sRuns well
55Good quality (B) · 55 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.Hermes 4 14BNous Research · 15BQ3_K_M10.1 GB12.2 tok/sRuns well
53Fair quality (C) · 53 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.EXAONE Deep 7.8BLG AI Research · 7.8BQ4_K_M7.4 GB17.9 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.TMax 4BAi2 · 4.2BQ4_K_M4.4 GB33.2 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)F168.7 GB44.1 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4B Thinking 2507Alibaba · 4.0BQ4_K_M5.2 GB34.7 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3 7B ThinkAi2 · 7.3BQ4_K_M7.5 GB19.1 tok/sRuns well
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL 4.7BMicrosoft · 4.7BQ4_K_M5.7 GB29.5 tok/sRuns well
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Agents-A1 4BInternScience · 4.5BQ4_K_M4.6 GB30.8 tok/sRuns great
51Fair quality (C) · 51 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 3.1 Nemotron Nano 8B v1NVIDIA · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
55Good quality (B) · 55 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.AceReason Nemotron 14BNVIDIA · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
55Good quality (B) · 55 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.OpenReasoning Nemotron 14BNVIDIA · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
55Good quality (B) · 55 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.Qwen2.5 Coder 14B InstructAlibaba · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
55Good quality (B) · 55 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.Apriel Nemotron 15B ThinkerServiceNow · 15BQ3_K_M10.6 GB12.1 tok/sRuns welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 8BShanghai AI Lab · 7.9BQ4_K_M6.9 GB17.6 tok/sRuns well
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4B Instruct 2507Alibaba · 4.0BQ4_K_M5.2 GB34.7 tok/sRuns great
37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)Q6_K8.5 GB52.4 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.LFM3 1.7BLiquid AI · 1.7BQ8_03.5 GB41.1 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 4B InstructAlibaba · 4.4BQ4_K_M5.5 GB31.5 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Fara 1.5 4BMicrosoft · 4.5BQ4_K_M4.6 GB30.8 tok/sRuns great
52Fair quality (C) · 52 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.JanusCoder 14BShanghai AI Lab · 15BQ3_K_M10.1 GB12.2 tok/sRuns well
53Fair quality (C) · 53 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.Falcon-H1R 7BTII · 7.6BQ4_K_M6.6 GB18.4 tok/sRuns well
39Basic quality (D) · 39 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.LFM2 24B-A2BLiquid AI · 24B (2.3B active)Q2_K11.3 GB76.0 tok/sRuns welltight fit
49Fair quality (C) · 49 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.Foundation-Sec 8B ReasoningCisco Foundation AI · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
52Fair quality (C) · 52 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.Qwen2.5 Coder 7B InstructAlibaba · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
53Fair quality (C) · 53 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.Phi-4 (14B)Microsoft · 15BQ3_K_M10.4 GB12.3 tok/sRuns welltight fit
53Fair quality (C) · 53 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.DeepCoder 14B PreviewAgentica · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
53Fair quality (C) · 53 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.InternVL3 14BShanghai AI Lab · 15BQ3_K_M10.6 GB11.9 tok/sRuns welltight fit
49Fair quality (C) · 49 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.Hunyuan 7B InstructTencent · 7.5BQ4_K_M7.2 GB18.6 tok/sRuns well
47Fair quality (C) · 47 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.Olmo 3 7B InstructAi2 · 7.3BQ4_K_M7.5 GB19.1 tok/sRuns well
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E4BGoogle · 7.9BQ4_K_M6.5 GB34.9 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)Q4_K_M11.4 GB48.7 tok/sRuns welltight fit
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.OpenReasoning Nemotron 7BNVIDIA · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 9B 0414Zhipu AI · 9.4BQ4_K_M7.6 GB14.9 tok/sRuns well
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM4 8BOpenBMB · 8.2BQ4_K_M6.8 GB17.1 tok/sRuns well
49Fair quality (C) · 49 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.Falcon 3 10B InstructTII · 10BQ4_K_M9.2 GB13.5 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Nanobeipo-ai · 9.4BQ4_K_M7.6 GB14.8 tok/sRuns well
49Fair quality (C) · 49 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.MiniCPM-o 2.6 8BOpenBMB · 8.7BQ4_K_M7.3 GB16.1 tok/sRuns well
47Fair quality (C) · 47 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.InternVL2.5 8BShanghai AI Lab · 8.1BQ4_K_M7.6 GB17.3 tok/sRuns well
47Fair quality (C) · 47 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.DeepSeek R1 Distill Llama 8BDeepSeek · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
47Fair quality (C) · 47 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.Foundation-Sec 1.1 8B InstructCisco Foundation AI · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
52Fair quality (C) · 52 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.Qwen2.5 14B InstructAlibaba · 15BQ3_K_M10.4 GB12.3 tok/sRuns welltight fit
52Fair quality (C) · 52 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.DeepSeek R1 Distill Qwen 14BDeepSeek · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
47Fair quality (C) · 47 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.Gemma 2 9B ITGoogle · 9.2BQ4_K_M8.8 GB15.1 tok/sRuns well
49Fair quality (C) · 49 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.Qwen2.5-VL 7B InstructAlibaba · 8.3BQ4_K_M7.1 GB16.8 tok/sRuns well
49Fair quality (C) · 49 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.Granite 4.2 3BIBM · 3.7BQ4_K_M4.5 GB38.2 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4BAlibaba · 4.0BQ4_K_M5.2 GB34.7 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B InstructAlibaba · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
47Fair quality (C) · 47 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.Qianfan-OCR 4BBaidu · 4.7BQ4_K_M5.7 GB29.5 tok/sRuns well
38Basic quality (D) · 38 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.Phi-3.5 Mini InstructMicrosoft · 3.8BQ4_K_M7.1 GB36.6 tok/sRuns great
50Fair quality (C) · 50 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.Qwen2.5 14B Instruct 1MAlibaba · 15BQ3_K_M10.4 GB12.2 tok/sRuns welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.InternLM3 8B InstructShanghai AI Lab · 8.8BQ4_K_M7.3 GB15.9 tok/sRuns well
45Fair quality (C) · 45 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.Hermes 3 (Llama 3.1 8B)Nous Research · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 8B InstructMeta · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Fara 7BMicrosoft · 8.3BQ4_K_M7.1 GB16.8 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 9B Chat 1MZhipu AI · 9.5BQ4_K_M8.0 GB14.7 tok/sRuns well
43Fair quality (C) · 43 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.Granite 3.2 8B InstructIBM · 8.2BQ4_K_M7.9 GB17.1 tok/sRuns well
43Fair quality (C) · 43 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.Granite 3.3 8BIBM · 8.2BQ4_K_M7.9 GB17.1 tok/sRuns well
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B Instruct 1MAlibaba · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
45Fair quality (C) · 45 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.GLM-4 9B Chat (2024)Zhipu AI · 9.4BQ4_K_M7.6 GB14.9 tok/sRuns well
43Fair quality (C) · 43 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.Ministral 8B (2410)Mistral AI · 8.0BQ4_K_M7.7 GB17.4 tok/sRuns well
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Mistral Nemo 12B InstructMistral AI · 12BQ4_K_M10.3 GB11.4 tok/sRuns welltight fit
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 7B InstructTII · 7.6BQ4_K_M6.6 GB18.4 tok/sRuns well
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 9BFastino · 7.9BQ4_K_M6.7 GB17.6 tok/sRuns well
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 26B-A4BGoogle · 26B (3.8B active)Q2_K12.3 GB43.2 tok/sRuns wellover memory limit
36Basic quality (D) · 36 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 Vision InstructMicrosoft · 4.2BQ4_K_M7.3 GB33.7 tok/sRuns great
43Fair quality (C) · 43 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 8BSwiss AI · 8.9BQ4_K_M8.1 GB15.7 tok/sRuns well
43Fair quality (C) · 43 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.DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
43Fair quality (C) · 43 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.Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
43Fair quality (C) · 43 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.Tülu 3 8BAi2 · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
43Fair quality (C) · 43 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.EXAONE 3.5 7.8BLG AI Research · 7.8BQ4_K_M7.4 GB17.9 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 2.6 8BOpenBMB · 8.1BQ4_K_M7.0 GB17.2 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 8B InstructIBM · 8.2BQ4_K_M7.9 GB17.1 tok/sRuns well
43Fair quality (C) · 43 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.Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8BQ4_K_M5.0 GB36.4 tok/sRuns great
49Fair quality (C) · 49 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.LFM3-VL 2BLiquid AI · 1.9BQ6_K3.2 GB50.5 tok/sRuns great
43Fair quality (C) · 43 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.Falcon 3 7B InstructTII · 7.5BQ4_K_M7.1 GB18.7 tok/sRuns well
43Fair quality (C) · 43 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.CodeGeeX4 All 9BZhipu AI · 9.4BQ4_K_M7.6 GB14.9 tok/sRuns well
34Basic quality (D) · 34 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.Phi-3 Mini 128K InstructMicrosoft · 3.8BQ4_K_M7.1 GB36.6 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Nano 4BNVIDIA · 4.0BQ4_K_M4.1 GB35.2 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Pixtral 12B (2409)Mistral AI · 12BQ4_K_M10.5 GB11.3 tok/sRuns welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Omni 7BAlibaba · 11BQ4_K_M8.6 GB13.0 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.InternVL2 8BShanghai AI Lab · 8.1BQ4_K_M7.6 GB17.3 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
41Fair quality (C) · 41 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.Hermes 2 Pro Llama 3 8BNous Research · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
41Fair quality (C) · 41 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.OpenChat 3.6 8BOpenChat · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
43Fair quality (C) · 43 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.North Micro VisionCohere · 2.5BQ6_K4.5 GB39.1 tok/sRuns great
42Fair quality (C) · 42 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.WeVisOne-VL 4BTencent · 4.8BQ4_K_M5.7 GB28.9 tok/sRuns well
43Fair quality (C) · 43 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.Granite 4.1 3BIBM · 3.4BQ4_K_M4.3 GB41.1 tok/sRuns great
41Fair quality (C) · 41 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.Phi-3 Small 8K InstructMicrosoft · 7.4BQ4_K_M7.1 GB18.9 tok/sRuns well
35Basic quality (D) · 35 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.Gemma 3n E2BGoogle · 5.4BQ6_K6.1 GB48.5 tok/sRuns great
38Basic quality (D) · 38 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.DeepSeek Prover V2 7BDeepSeek · 6.9BQ4_K_M9.8 GB20.2 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini (3.8B)Microsoft · 3.8BQ4_K_M5.0 GB36.4 tok/sRuns great
43Fair quality (C) · 43 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.DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
46Fair quality (C) · 46 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.Reka Flash 3.1 (21B)Reka AI · 21BQ2_K11.0 GB11.0 tok/sRuns welltight fit
39Basic quality (D) · 39 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.Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4BQ4_K_M8.0 GB16.6 tok/sRuns well
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.LightOnOCR-3 4BLightOn · 4.5BQ4_K_M4.6 GB30.8 tok/sRuns great
61Good quality (B) · 61 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.Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active)Q2_K13.1 GB38.9 tok/sRuns wellover memory limit
45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Chandra OCR 2Datalab · 5.3BQ4_K_M5.1 GB26.4 tok/sRuns well
41Fair quality (C) · 41 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.Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5BQ4_K_M5.4 GB31.0 tok/sRuns great
32Basic quality (D) · 32 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.Phi-3 Vision 128K InstructMicrosoft · 4.2BQ4_K_M7.3 GB33.7 tok/sRuns great
39Basic quality (D) · 39 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.Llama 3 8B InstructMeta · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
41Fair quality (C) · 41 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.Ministral 3 3BMistral AI · 3.9BQ4_K_M4.8 GB36.3 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Multimodal InstructMicrosoft · 5.6BQ4_K_M6.0 GB25.1 tok/sRuns well
41Fair quality (C) · 41 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.Aya Vision 8BCohere · 8.6BQ4_K_M7.2 GB16.2 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 7B InstructAlibaba · 8.3BQ4_K_M7.1 GB16.8 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 4B InstructTencent · 4.2BQ4_K_M5.3 GB33.1 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Command R7BCohere · 8.0BQ4_K_M6.8 GB17.4 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 7B InstructAlibaba · 7.6BQ4_K_M6.7 GB18.3 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)Q8_09.4 GB45.3 tok/sRuns great
39Basic quality (D) · 39 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 3.2 11B Vision InstructMeta · 11BQ4_K_M9.4 GB13.1 tok/sRuns well
38Basic quality (D) · 38 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 8B InstructSwiss AI · 8.1BQ4_K_M7.5 GB17.3 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 8BCohere · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
38Basic quality (D) · 38 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.Yi Coder 9B Chat01.AI · 8.8BQ4_K_M7.8 GB15.8 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 7B ChatShanghai AI Lab · 7.7BQ4_K_M7.4 GB18.0 tok/sRuns well
42Fair quality (C) · 42 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.Gemma 3 4B ITGoogle · 4.3BQ4_K_M4.4 GB32.5 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium (14B)Microsoft · 14BQ4_K_M10.9 GB10.0 tok/sRuns welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium 128K InstructMicrosoft · 14BQ4_K_M11.8 GB10.0 tok/sRuns welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 2.6BLiquid AI · 2.7BQ5_K_M3.6 GB42.7 tok/sRuns great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Command R7B ArabicCohere · 8.0BQ4_K_M6.8 GB17.4 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 4B ITGoogle · 4.3BQ4_K_M4.4 GB32.5 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 8B InstructIBM · 8.2BQ4_K_M7.2 GB17.1 tok/sRuns well
34Basic quality (D) · 34 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.OLMo 2 7B InstructAi2 · 7.3BQ4_K_M8.2 GB19.1 tok/sRuns well
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.SmolLM3 3BHugging Face · 3.1BQ4_K_M4.0 GB45.3 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5-VL 3BLiquid AI · 3.1BQ4_K_M3.6 GB44.8 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.TeleOCRXingChen-AGI · 1.4BQ8_04.0 GB50.1 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 SOLAR 10.7BNous Research · 11BQ4_K_M8.9 GB13.0 tok/sRuns well
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.SOLAR 10.7B InstructUpstage · 11BQ4_K_M8.9 GB13.0 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 9B V2LLM4Binary · 8.8BQ4_K_M7.8 GB15.8 tok/sRuns well
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Jamba Reasoning 3BAI21 Labs · 3.2BQ4_K_M3.5 GB43.6 tok/sRuns great
42Fair quality (C) · 42 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.Solar Pro Preview 22BUpstage · 22BQ2_K11.8 GB10.4 tok/sRuns welltight fit
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 Micro (3B)IBM · 3.4BQ4_K_M4.3 GB41.1 tok/sRuns great
32Basic quality (D) · 32 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 6.7B InstructDeepSeek · 6.7BQ4_K_M10.0 GB20.7 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 4K InstructMicrosoft · 3.8BQ4_K_M5.5 GB36.6 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.3Mistral AI · 7.3BQ4_K_M7.1 GB19.3 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Jamba2 3BAI21 Labs · 3.0BQ5_K_M3.7 GB38.1 tok/sRuns great
42Fair quality (C) · 42 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.MiniCPM-OCR 1.0 1.3BOpenBMB · 1.3BQ8_03.0 GB54.7 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.AFM 4.5BArcee AI · 4.6BQ4_K_M5.0 GB30.2 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 7B InstructZyphra · 7.4BQ4_K_M6.8 GB19.0 tok/sRuns well
39Basic quality (D) · 39 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.Qwen3.5 2BAlibaba · 2.3BQ6_K3.5 GB42.7 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)Q2_K12.3 GB41.3 tok/sRuns wellover memory limit
30Basic quality (D) · 30 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.LLM4Decompile 6.7B V2LLM4Binary · 6.7BQ4_K_M10.0 GB20.7 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.0 7.8B InstructLG AI Research · 7.8BQ4_K_M6.9 GB17.9 tok/sRuns well
34Basic quality (D) · 34 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.Hermes 2 Pro Mistral 7BNous Research · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B BetaNexusflow · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.7 1BOpenBMB · 1.6BQ8_03.3 GB45.9 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)Q4_K_M11.9 GB44.1 tok/sRuns welltight fit
36Basic quality (D) · 36 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.OLMo 2 13B InstructAi2 · 14BQ3_K_M11.6 GB13.2 tok/sRuns welltight fit
35Basic quality (D) · 35 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.Qwen3-VL 2B InstructAlibaba · 2.1BQ6_K4.2 GB45.5 tok/sRuns great
42Fair quality (C) · 42 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.PaddleOCR-VL 1.6 0.9BBaidu · 1.0BQ8_02.7 GB74.1 tok/sRuns great
39Basic quality (D) · 39 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.TMax 2BAi2 · 1.9BQ6_K3.2 GB51.5 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 9B Chat01.AI · 8.8BQ4_K_M7.3 GB15.8 tok/sRuns well
33Basic quality (D) · 33 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.OpenChat 3.5 (0106)OpenChat · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Aya 23 8BCohere · 8.0BQ4_K_M7.5 GB17.4 tok/sRuns well
21Basic quality (D) · 21 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.DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)Q3_K_M10.5 GB53.3 tok/sRuns welltight fit
34Basic quality (D) · 34 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.Voxtral Mini 3BMistral AI · 4.7BQ4_K_M5.4 GB29.8 tok/sRuns well
28Basic quality (D) · 28 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.CodeGemma 7BGoogle · 8.5BQ3_K_M9.5 GB21.1 tok/sRuns well
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss 20BOpenAI · 21B (3.6B active)MXFP413.7 GB31.0 tok/sSlowfar over memory limit
28Basic quality (D) · 28 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.SQLCoder 7B v2Defog · 6.7BQ4_K_M10.0 GB20.7 tok/sRuns well
33Basic quality (D) · 33 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.Llama 3.2 3B InstructMeta · 3.2BQ4_K_M4.5 GB43.5 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Mathstral 7BMistral AI · 7.3BQ4_K_M7.1 GB19.3 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.2Mistral AI · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mistral 7B DPONous Research · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (1210)OpenChat · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
36Basic quality (D) · 36 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.MiniCPM3 4BOpenBMB · 4.1BQ4_K_M4.3 GB34.3 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 8B Instruct (128K)IBM · 8.1BQ4_K_M7.7 GB17.3 tok/sRuns well
36Basic quality (D) · 36 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.Falcon3 Mamba 7B InstructTII · 7.3BQ4_K_M6.0 GB19.2 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H MicroIBM · 3.2BQ4_K_M3.6 GB43.8 tok/sRuns great
33Basic quality (D) · 33 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.StarCoder2 15B InstructBigCode · 16BQ3_K_M10.1 GB11.3 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.RecurrentGemma 9B ITGoogle · 9.6BQ4_K_M7.5 GB14.5 tok/sRuns well
34Basic quality (D) · 34 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.Qwen2.5-Math 7B InstructAlibaba · 7.6BQ4_K_M6.4 GB18.3 tok/sRuns well
30Basic quality (D) · 30 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.InternLM2 Math Plus 7BShanghai AI Lab · 7.7BQ4_K_M7.4 GB18.0 tok/sRuns well
35Basic quality (D) · 35 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.InternLM2.5 20B ChatShanghai AI Lab · 20BQ2_K11.1 GB11.5 tok/sRuns welltight fit
35Basic quality (D) · 35 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.S5 nanoMaritaca AI · 4.7BQ4_K_M4.7 GB30.0 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.OpenHermes 2.5 Mistral 7BTeknium · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
30Basic quality (D) · 30 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.Starling LM 7B AlphaBerkeley · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 3B InstructTII · 3.2BQ4_K_M3.7 GB44.3 tok/sRuns great
34Basic quality (D) · 34 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.Qwen2.5 Coder 3B InstructAlibaba · 3.1BQ4_K_M3.7 GB45.2 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Codestral Mamba 7BMistral AI · 7.3BQ4_K_M6.0 GB19.2 tok/sRuns well
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 Llama 3.2 3BNous Research · 3.2BQ4_K_M4.5 GB43.5 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 3B InstructAlibaba · 3.8BQ4_K_M4.1 GB37.2 tok/sRuns great
28Basic quality (D) · 28 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.Mistral 7B Instruct v0.1Mistral AI · 7.2BQ4_K_M7.1 GB19.3 tok/sRuns well
36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 1BOpenBMB · 1.1BQ8_02.9 GB65.8 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 3B InstructAlibaba · 3.1BQ4_K_M3.7 GB45.2 tok/sRuns great
61Good quality (B) · 61 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.GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)Q2_K14.5 GB52.5 tok/sSlowfar over memory limit
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.LFM2 2.6BLiquid AI · 2.6BQ5_K_M3.5 GB44.9 tok/sRuns great
23Basic quality (D) · 23 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 1.1 7B ITGoogle · 8.5BQ3_K_M9.5 GB21.1 tok/sRuns well
16Basic quality (D) · 16 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.Code Llama 7B InstructMeta · 6.7BQ2_K8.6 GB34.0 tok/sRuns great
29Basic quality (D) · 29 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.EXAONE 3.5 2.4BLG AI Research · 2.4BQ6_K4.2 GB40.2 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 1.7BAlibaba · 2.0BQ6_K4.2 GB47.7 tok/sRuns great
21Basic quality (D) · 21 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.Qwen1.5 7B ChatAlibaba · 7.7BQ3_K_M9.6 GB23.4 tok/sRuns well
28Basic quality (D) · 28 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.Falcon 3 3B InstructTII · 3.2BQ4_K_M4.3 GB43.2 tok/sRuns great
29Basic quality (D) · 29 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.Granite 3.2 2B InstructIBM · 2.5BQ5_K_M4.0 GB45.6 tok/sRuns great
29Basic quality (D) · 29 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.Granite 3.3 2BIBM · 2.5BQ5_K_M4.0 GB45.6 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 3B Instruct (128K)IBM · 3.5BQ4_K_M6.4 GB40.1 tok/sRuns great
46Fair quality (C) · 46 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.Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)Q2_K12.2 GB52.5 tok/sRuns wellover memory limit
59Good quality (B) · 59 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.Hunyuan Hy-Memory 30B-A3BTencent · 30B (3.0B active)Q2_K14.4 GB52.5 tok/sSlowfar over memory limit
21Basic quality (D) · 21 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.Gemma 7B ITGoogle · 8.5BQ3_K_M9.5 GB21.1 tok/sRuns well
19Basic quality (D) · 19 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.Stable Code Instruct 3BStability AI · 2.8BQ5_K_M6.2 GB41.2 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.WeVisOne VL 2BTencent · 2.4BQ6_K4.5 GB39.7 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM2 2.2B InstructHugging Face · 2.3BQ6_K5.0 GB43.1 tok/sRuns great
29Basic quality (D) · 29 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.InternLM2 Chat 20BShanghai AI Lab · 20BQ2_K11.1 GB11.5 tok/sRuns welltight fit
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.0 1.2BLG AI Research · 1.3BQ8_03.4 GB55.5 tok/sRuns great
26Basic quality (D) · 26 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.StarCoder2 15B (base)BigCode · 16BQ3_K_M10.1 GB11.3 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 12B ChatStability AI · 12BQ4_K_M9.8 GB11.5 tok/sRuns well
32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 1.2B InstructLiquid AI · 1.2BQ8_02.9 GB60.8 tok/sRuns great
27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 2B InstructIBM · 2.5BQ5_K_M4.0 GB45.6 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Falcon Mamba 7B InstructTII · 7.3BQ4_K_M6.0 GB19.2 tok/sRuns well
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)Q8_05.6 GB66.4 tok/sRuns great
27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 2BGoogle · 2.6BQ5_K_M3.9 GB44.2 tok/sRuns great
63Good quality (B) · 63 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.TMax 27BAi2 · 27BQ2_K13.0 GB7.1 tok/sSlowover memory limit
28Basic quality (D) · 28 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.InternLM2 Math Plus 20BShanghai AI Lab · 20BQ2_K11.1 GB11.5 tok/sRuns welltight fit
21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 2.2B InstructHugging Face · 2.3BQ6_K5.0 GB43.1 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 Mistral 7BLLaVA · 7.6BQ3_K_M6.3 GB23.9 tok/sRuns well
25Basic quality (D) · 25 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.Granite Code 20B InstructIBM · 20BQ2_K9.8 GB11.4 tok/sRuns well
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Neural Chat 7B v3.3Intel · 7.2BQ3_K_M6.2 GB24.9 tok/sRuns well
56Good quality (B) · 56 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 Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)Q2_K14.2 GB46.2 tok/sSlowfar over memory limit
56Good quality (B) · 56 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.North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)Q2_K14.1 GB52.5 tok/sSlowfar over memory limit
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.Fara 1.5 27BMicrosoft · 27BQ2_K13.0 GB7.1 tok/sSlowover memory limit
24Basic quality (D) · 24 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 Vision 3.2 2BIBM · 3.0BQ4_K_M4.0 GB46.9 tok/sRuns great
19Basic quality (D) · 19 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.Orca 2 13BMicrosoft · 13BQ2_K10.1 GB17.6 tok/sRuns well
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.DeepScaleR 1.5B PreviewAgentica · 1.8BQ8_03.7 GB39.9 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H 1BIBM · 1.5BQ8_03.2 GB48.7 tok/sRuns great
25Basic quality (D) · 25 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.Qwen2.5-Omni 3BAlibaba · 5.5BQ3_K_M4.6 GB32.6 tok/sRuns great
25Basic quality (D) · 25 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 2B InstructIBM · 2.6BQ5_K_M3.8 GB43.9 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 1.7B InstructHugging Face · 1.7BQ8_05.0 GB41.6 tok/sRuns great
54Fair quality (C) · 54 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.Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)Q2_K14.6 GB48.5 tok/sSlowfar over memory limit
54Fair quality (C) · 54 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.Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)Q2_K14.6 GB48.5 tok/sSlowfar over memory limit
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.WizardMath 7B v1.1WizardLM · 7.2BQ3_K_M6.2 GB24.9 tok/sRuns well
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Zephyr 7B BetaHugging Face · 7.2BQ3_K_M6.2 GB24.9 tok/sRuns well
18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)Q8_05.4 GB66.4 tok/sRuns great
60Good quality (B) · 60 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.UI-Mate 27BTencent · 27BQ2_K13.0 GB7.1 tok/sSlowover memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 1.5B InstructAlibaba · 1.5BQ8_03.4 GB46.2 tok/sRuns great
53Fair quality (C) · 53 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.Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)Q2_K14.2 GB46.2 tok/sSlowfar over memory limit
53Fair quality (C) · 53 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.Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)Q2_K14.6 GB48.5 tok/sSlowfar over memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 1.5B InstructTII · 1.6BQ8_03.4 GB45.9 tok/sRuns great
18Basic quality (D) · 18 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.Llama 2 13B ChatMeta · 13BQ2_K10.1 GB17.6 tok/sRuns well
15Basic quality (D) · 15 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.Orca 2 7BMicrosoft · 6.7BQ2_K6.4 GB34.0 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.StarCoder 15BBigCode · 16BQ3_K_M9.5 GB11.4 tok/sRuns well
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 6B Chat01.AI · 6.1BQ3_K_M4.8 GB29.8 tok/sRuns well
23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 2B InstructAlibaba · 2.2BQ6_K3.6 GB43.8 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 1.8B InstructTencent · 1.8BQ8_04.0 GB39.7 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 7B ChatMeta · 6.7BQ2_K6.4 GB34.0 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 1.5B InstructAlibaba · 1.5BQ8_03.4 GB46.2 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Baichuan 2 13B ChatBaichuan · 14BQ3_K_M11.7 GB13.0 tok/sRuns welltight fit
14Basic quality (D) · 14 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.Baichuan 2 7B ChatBaichuan · 7.5BQ2_K6.7 GB30.5 tok/sRuns great
51Fair quality (C) · 51 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.Qwen3 30B-A3BAlibaba · 31B (3.3B active)Q2_K14.6 GB48.5 tok/sSlowfar over memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.LFM2 1.2BLiquid AI · 1.2BQ8_02.9 GB60.8 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 1.6BLiquid AI · 1.6BQ8_03.3 GB45.0 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8BQ8_03.7 GB39.9 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 2.7B InstructZyphra · 2.7BQ5_K_M3.8 GB43.4 tok/sRuns great
15Basic quality (D) · 15 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.WizardLM 13B v1.2WizardLM · 13BQ2_K10.1 GB17.6 tok/sRuns well
50Fair quality (C) · 50 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 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)Q2_K14.2 GB52.5 tok/sSlowfar over memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 0.8BAlibaba · 0.9BQ8_02.6 GB81.7 tok/sRuns great
12Basic quality (D) · 12 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.DeepSeek LLM 7B ChatDeepSeek · 6.9BQ2_K6.3 GB33.2 tok/sRuns great
15Basic quality (D) · 15 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.StableLM Zephyr 3BStability AI · 2.8BQ5_K_M4.9 GB41.2 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 1.5B Chat01.AI · 1.5BQ8_04.7 GB48.0 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Mini 4B InstructNVIDIA · 4.2BQ3_K_M4.1 GB43.1 tok/sRuns great
14Basic quality (D) · 14 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.Vicuna 13B v1.5LMSYS · 13BQ2_K10.1 GB17.6 tok/sRuns well
11Basic quality (D) · 11 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.LLaVA 1.5 7BLLaVA · 7.1BQ2_K6.5 GB32.5 tok/sRuns great
49Fair quality (C) · 49 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.Sarvam 30BSarvam AI · 32B (2.4B active)Q2_K14.6 GB62.6 tok/sSlowfar over memory limit
18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 13BLLaVA · 13BQ3_K_M11.5 GB13.5 tok/sRuns welltight fit
22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 1B InstructMeta · 1.2BQ8_03.1 GB57.3 tok/sRuns great
53Fair quality (C) · 53 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.Devstral Small 2 (24B)Mistral AI · 24BQ2_K12.5 GB8.1 tok/sSlowover memory limit
20Basic quality (D) · 20 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.d1 2BLiquid AI · 1.9BQ6_K3.2 GB50.5 tok/sRuns great
9Basic quality (D) · 9 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.Vicuna 7B v1.5LMSYS · 6.7BQ2_K6.4 GB34.0 tok/sRuns great
17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 1.8B ChatShanghai AI Lab · 1.9BQ6_K3.9 GB51.3 tok/sRuns great
16Basic quality (D) · 16 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.StarCoder2 7BBigCode · 7.2BQ2_K5.0 GB32.0 tok/sRuns great
66Good quality (B) · 66 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.Qwen3.8 27BAlibaba · 28BQ2_K13.2 GB7.0 tok/sSlowfar over memory limit
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 1.5B InstructAlibaba · 1.5BQ8_03.3 GB46.2 tok/sRuns great
15Basic quality (D) · 15 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.Phi-2 2.7BMicrosoft · 2.8BQ5_K_M4.2 GB41.5 tok/sRuns great
65Good quality (B) · 65 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.Qwen3.6 27BAlibaba · 28BQ2_K13.2 GB7.0 tok/sSlowfar over memory limit
16Basic quality (D) · 16 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.Falcon 3 1B InstructTII · 1.7BQ8_03.9 GB42.6 tok/sRuns great
17Basic quality (D) · 17 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.StarCoder2 3BBigCode · 3.0BQ4_K_M3.7 GB46.1 tok/sRuns great
65Good quality (B) · 65 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.Qwen3.5 27BAlibaba · 28BQ2_K13.2 GB7.0 tok/sSlowfar over memory limit
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 1.2 (24B)Mistral AI · 24BQ2_K12.5 GB8.1 tok/sSlowover memory limit
12Basic quality (D) · 12 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.DeepSeek Coder 1.3B InstructDeepSeek · 1.4BQ8_04.6 GB52.7 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 1.3B V2LLM4Binary · 1.4BQ8_04.6 GB52.7 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.LFM2 700MLiquid AI · 0.7BF163.1 GB44.3 tok/sRuns great
20Basic quality (D) · 20 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.Gemma 3 1BGoogle · 1.0BQ8_02.7 GB71.1 tok/sRuns great
14Basic quality (D) · 14 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.Yi 6B Chat01.AI · 6.1BQ2_K4.3 GB37.9 tok/sRuns great
64Good quality (B) · 64 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.Muse Glimmer 30BMeta · 30BQ2_K13.6 GB6.5 tok/sSlowfar over memory limit
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 0.6BAlibaba · 0.8BF164.0 GB43.7 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Spark X2.6 1.7BSparkLLM · 1.7BQ8_03.5 GB41.6 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 1.1 (24B)Mistral AI · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 2507Mistral AI · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 1.5B InstructAlibaba · 1.5BQ8_03.4 GB46.2 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 2BFastino · 1.9BQ6_K3.2 GB51.5 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 1.7B InstructHugging Face · 1.7BQ8_03.8 GB41.6 tok/sRuns great
9Basic quality (D) · 9 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.OLMo 7B InstructAi2 · 6.9BQ2_K5.4 GB33.3 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 27B Text ITGoogle · 27BQ2_K13.2 GB7.2 tok/sSlowover memory limit
14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 1B InstructAi2 · 1.5BQ8_03.7 GB48.0 tok/sRuns great
47Fair quality (C) · 47 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.Magistral Small 2506Mistral AI · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
47Fair quality (C) · 47 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.Mistral Small 3.2 24BMistral AI · 24BQ2_K12.5 GB8.1 tok/sSlowover memory limit
13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 2BGoogle · 2.5BQ5_K_M3.5 GB46.0 tok/sRuns great
8Basic quality (D) · 8 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.InternLM 7BShanghai AI Lab · 7.3BQ2_K5.6 GB31.3 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 2505Mistral AI · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
15Basic quality (D) · 15 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.surya ocr 2.5Datalab · 0.7BF163.0 GB47.5 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3.1 24BMistral AI · 24BQ2_K12.5 GB8.1 tok/sSlowover memory limit
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Hemmingway 1.5Hemmingway · 27BQ2_K12.9 GB7.2 tok/sSlowover memory limit
10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 1.6B ChatStability AI · 1.6BQ8_04.1 GB43.4 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 Zephyr 1.6BStability AI · 1.6BQ8_04.1 GB43.4 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.SenseNova 6.8 Code2VideoSenseTime · 27BQ2_K13.0 GB7.1 tok/sSlowover memory limit
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3 24B (2501)Mistral AI · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2B ITGoogle · 2.5BQ5_K_M3.5 GB46.0 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 0.5B InstructTII · 0.5BF162.8 GB63.0 tok/sRuns great
43Fair quality (C) · 43 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.Codestral 22BMistral AI · 22BQ2_K12.3 GB8.8 tok/sSlowover memory limit
43Fair quality (C) · 43 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.Dolphin Mistral 24B Venice EditionCognitive Computations · 24BQ2_K12.5 GB8.1 tok/sSlowover memory limit
43Fair quality (C) · 43 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.Voxtral Small 24BMistral AI · 24BQ2_K12.6 GB8.0 tok/sSlowover memory limit
11Basic quality (D) · 11 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 0.8BFastino · 0.8BF163.2 GB43.7 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 350MLiquid AI · 0.4BF162.4 GB93.6 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24BQ2_K12.3 GB8.3 tok/sSlowover memory limit
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 450MLiquid AI · 0.5BF162.6 GB72.8 tok/sRuns great
40Fair quality (C) · 40 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.LLM4Decompile 22B V2LLM4Binary · 22BQ2_K12.3 GB8.8 tok/sSlowover memory limit
8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 0.5B InstructTencent · 0.5BF163.4 GB60.7 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 500M InstructHugging Face · 0.5BF162.9 GB64.3 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.LFM2 350MLiquid AI · 0.4BF162.4 GB93.6 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H 350MIBM · 0.3BF162.3 GB96.4 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 0.5B InstructAlibaba · 0.5BF162.6 GB66.9 tok/sRuns great
43Fair quality (C) · 43 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 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)Q2_K14.6 GB20.1 tok/sSlowfar over memory limit
37Basic quality (D) · 37 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.Mistral Small 22B (2409)Mistral AI · 22BQ2_K12.3 GB8.8 tok/sSlowover memory limit
4Basic quality (D) · 4 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.Falcon 7B InstructTII · 7.2BQ2_K4.5 GB31.8 tok/sRuns great
8Basic quality (D) · 8 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.Qwen2.5 Coder 0.5B InstructAlibaba · 0.5BF162.6 GB66.9 tok/sRuns great
8Basic quality (D) · 8 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.SmolLM2 360M InstructHugging Face · 0.4BF162.6 GB91.0 tok/sRuns great
10Basic quality (D) · 10 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 230MLiquid AI · 0.2BF162.1 GB142 tok/sRuns great
6Basic quality (D) · 6 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.TinyLlama 1.1B ChatTinyLlama · 1.1BQ8_02.8 GB64.6 tok/sRuns great
50Fair quality (C) · 50 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.Gemma 3 27B ITGoogle · 27BQ2_K13.3 GB7.1 tok/sSlowfar over memory limit
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 0.5B InstructAlibaba · 0.5BF162.6 GB66.9 tok/sRuns great
6Basic quality (D) · 6 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.ERNIE 4.5 0.3BBaidu · 0.4BF162.4 GB91.0 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM 256M InstructHugging Face · 0.3BF162.3 GB126 tok/sRuns great
6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 270MGoogle · 0.3BF162.1 GB121 tok/sRuns great
5Basic quality (D) · 5 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.SmolLM 360M InstructHugging Face · 0.4BF162.4 GB91.0 tok/sRuns great
47Fair quality (C) · 47 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.Terminal RSI 27BTeriminal-RSI · 28BQ2_K13.2 GB7.0 tok/sSlowfar over memory limit
4Basic quality (D) · 4 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.SmolLM2 135M InstructHugging Face · 0.1BF162.0 GB252 tok/sRuns great
3Basic quality (D) · 3 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.Falcon-H1 Tiny 90M InstructTII · 0.1BF161.8 GB364 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 27B ITGoogle · 27BQ2_K14.2 GB7.2 tok/sSlowfar over memory limit
2Basic quality (D) · 2 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 135M InstructHugging Face · 0.1BF161.9 GB252 tok/sRuns great
23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 14B ChatAlibaba · 14BQ2_K13.9 GB13.8 tok/sSlowfar over memory limit
25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 13B InstructMeta · 13BQ3_K_M14.7 GB11.8 tok/sSlowfar over memory limit
26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking.CogVLM2 Llama 3 Chat 19BZhipu AI · 20BQ2_K13.7 GB10.0 tok/sSlowfar over memory limit
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)MXFP468.5 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_K1,114 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_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.GLM-5.3 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K304 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_K981 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_K1,114 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_K412 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_K230 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_K174 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_K244 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_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.MiMo V2.6 Flash (310B-A15B)Xiaomi · 311B (15.0B active)Q2_K126 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_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.Mistral Large 4 (1T-A52B)Mistral AI · 1,053B (52.0B active)Q2_K423 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_K73.8 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_K304 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_K314 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_K331 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_K662 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_K413 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Nanbeige4.3 33BBOSS Zhipin (Nanbeige) · 33BQ2_K16.6 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_K230 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_K411 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_K163 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_K304 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_K161 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_K642 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_K125 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 397B-A17BAlibaba · 403B (17.0B active)Q2_K163 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_K173 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_K304 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_K155 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_K124 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_K202 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_K413 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Kimi K2.7 Code (1T)Moonshot AI · 1,027B (32.0B active)Q2_K413 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_K124 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_K126 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_K163 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Super VL 120B-A12BNVIDIA · 124B (12.0B active)Q2_K51.4 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_K276 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_K108 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_K148 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_K383 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_K95.1 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.Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)Q2_K16.1 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_K82.5 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.MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active)Q2_K15.8 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_K226 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_K276 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_K413 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.Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)Q2_K16.1 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.Ornith 1.5 122B-A10BDeepReinforce · 125B (10.0B active)Q2_K51.8 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_K276 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_K412 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_K95.1 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.Nemotron 3.5 Bolt 74B-A9BNVIDIA · 75B (9.0B active)Q2_K31.6 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_K271 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_K118 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.Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active)Q2_K15.8 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)Q2_K51.8 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_K81.7 GB—Won't run
64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V3.1 TerminusDeepSeek · 685B (37.0B 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.DeepSeek V3.1 (671B)DeepSeek · 685B (37.0B 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.Gemma 4 31BGoogle · 31BQ2_K15.7 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active)Q2_K15.6 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_K413 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.Kolibri 1 (78B-A3.5B)Aleph Alpha · 78B (3.5B active)Q2_K33.0 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_K95.1 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_K97.2 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_K196 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.Sage-A1.5 35B-A3BInternScience · 36B (3.0B active)Q2_K16.1 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_K126 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.Flint (40B-A2.5B)Recursive · 40B (2.5B active)Q2_K17.7 GB—Won't run
63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Ling 1TAnt Group (inclusionAI) · 1,000B (50.0B active)Q2_K404 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_K272 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.Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)Q2_K16.1 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_K97.2 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_K103 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.Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)Q2_K16.1 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_K413 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_K95.1 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.Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)Q2_K16.1 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_K97.4 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Command A+ (218B-A25B)Cohere · 219B (25.0B active)Q2_K89.3 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_K96.8 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_K227 GB—Won't run
61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Super 120B-A12BNVIDIA · 124B (12.0B active)Q2_K51.1 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_K97.1 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Agents-A1 35B-A3BInternScience · 35B (3.0B active)Q2_K15.8 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)Q2_K15.6 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Devstral 2 (123B)Mistral AI · 125BQ2_K54.5 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_K99.4 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Laguna S 2.1 (118B-A8B)Poolside · 118B (8.0B active)Q2_K50.2 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_K107 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.Qwen3 Coder Next (80B-A3B)Alibaba · 80B (3.0B active)Q2_K33.6 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.Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)Q2_K34.3 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_K97.2 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_K147 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.Qwen3 Next 80B-A3B InstructAlibaba · 81B (3.0B active)Q2_K34.3 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_K276 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.6VZhipu AI · 108B (12.0B active)Q2_K46.2 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_K184 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Command A Reasoning (111B)Cohere · 111BQ2_K46.7 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.EXAONE 4.5 33BLG AI Research · 34BQ2_K16.0 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_K148 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.Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)Q2_K16.3 GB—Won't run
57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 Flash (127B-A5B)Ant Group (inclusionAI) · 127B (5.1B active)Q2_K53.0 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_K184 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 4 (119B-A6B)Mistral AI · 119B (6.0B active)Q2_K49.5 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_K55.6 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_K162 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Command A (111B)Cohere · 111BQ2_K46.7 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_K124 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5VZhipu AI · 108B (12.0B active)Q2_K46.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4 405BNous Research · 406BQ2_K168 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.Kimi Dev 72BMoonshot AI · 73BQ2_K33.3 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling 2.6 Flash (104B-A7.4B)Ant Group (inclusionAI) · 107B (7.4B active)Q2_K44.6 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.Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50BQ2_K24.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 2.1 (2411)Mistral AI · 123BQ2_K53.6 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.Seed-OSS 36B InstructByteDance · 36BQ2_K18.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Solar Open 100BUpstage · 103B (12.0B active)Q2_K44.2 GB—Won't run
55Good quality (B) · 55 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 4.3 36BNous Research · 36BQ2_K18.2 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)Q2_K47.3 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Mistral Large 2 (123B)Mistral AI · 123BQ2_K53.7 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Probeipo-ai · 397B (17.0B active)Q2_K161 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Pixtral Large 124B (2411)Mistral AI · 124BQ2_K54.1 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.Qwen3-VL 32B InstructAlibaba · 33BQ2_K17.1 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.QwQ 32BAlibaba · 33BQ2_K16.8 GB—Won't run
54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ring Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K43.3 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_K67.0 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.Granite 4.2 30BIBM · 29BQ2_K15.4 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.InternVL3.5 38BShanghai AI Lab · 38BQ2_K19.1 GB—Won't run
53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K43.3 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_K184 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.Olmo 3.1 32B ThinkAi2 · 32BQ2_K15.2 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.OpenReasoning Nemotron 32BNVIDIA · 33BQ2_K16.8 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.Qwen3 32BAlibaba · 33BQ2_K16.8 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.Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)Q2_K14.8 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.Skywork OR1 32BSkywork · 33BQ2_K16.8 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_K168 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_K271 GB—Won't run
52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Sarvam 105BSarvam AI · 106B (10.0B active)Q2_K44.3 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_K96.4 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.EXAONE Deep 32BLG AI Research · 32BQ2_K16.5 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.GLM-4 32B 0414Zhipu AI · 33BQ2_K15.1 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.GLM-Z1 32B (0414)Zhipu AI · 33BQ2_K15.1 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.Hermes 4 70BNous Research · 71BQ2_K32.5 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.Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)Q2_K34.8 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.InternVL3 78BShanghai AI Lab · 78BQ2_K35.6 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.Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)Q2_K21.3 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Leanstral 119B-A6BMistral AI · 119B (6.5B active)Q2_K49.5 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.Llama 3.3 70B InstructMeta · 71BQ2_K32.5 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.Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)Q2_K14.8 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.Qwen2.5 72B InstructAlibaba · 73BQ2_K33.3 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.Qwen2.5-VL 72B InstructAlibaba · 73BQ2_K33.6 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_K96.4 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 R1 Distill Llama 70BDeepSeek · 71BQ2_K32.5 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 R1 Distill Qwen 32BDeepSeek · 33BQ2_K16.8 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_K96.4 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.EXAONE 4.0 32BLG AI Research · 32BQ2_K15.1 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 30BIBM · 29BQ2_K15.3 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_K168 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_K164 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 4 Scout 17B-16EMeta · 109B (17.0B active)Q2_K46.6 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.Olmo 3.1 32B InstructAi2 · 32BQ2_K15.2 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.Tülu 3 70BAi2 · 71BQ2_K32.5 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.Baichuan M2 32BBaichuan · 33BQ2_K16.8 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.Command R+ (08-2024) 104BCohere · 104BQ2_K45.2 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2.5DeepSeek · 236B (21.0B active)Q2_K96.4 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Groot 65B A6B 261023GrootTeam · 118B (6.0B active)Q2_K49.1 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.InternVL3 38BShanghai AI Lab · 38BQ2_K19.1 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_K161 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.Llama 3.1 70B InstructMeta · 71BQ2_K32.5 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.OpenHands LM 32BAll Hands AI · 33BQ2_K16.8 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.Qwen2.5 32B InstructAlibaba · 33BQ2_K16.8 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.Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)Q2_K16.5 GB—Won't run
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 (Llama 3.1 70B)Nous Research · 71BQ2_K32.5 GB—Won't run
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 flash SanteAnt Group (inclusionAI) · 127B (5.1B active)Q2_K52.6 GB—Won't run
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.QVQ 72B PreviewAlibaba · 73BQ2_K33.6 GB—Won't run
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 32B InstructAlibaba · 33BQ2_K17.1 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 32B InstructAlibaba · 33BQ2_K16.8 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Apertus v1.5 70BSwiss AI · 72BQ2_K33.0 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron 70B InstructNVIDIA · 71BQ2_K32.5 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 90B Vision InstructMeta · 89BQ2_K40.4 GB—Won't run
46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32B PreviewAlibaba · 33BQ2_K16.8 GB—Won't run
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Command R+ 104B (04-2024)Cohere · 104BQ2_K45.2 GB—Won't run
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 34B InstructTII · 34BQ2_K16.2 GB—Won't run
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 72B InstructAlibaba · 73BQ2_K33.3 GB—Won't run
44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 72B InstructAlibaba · 73BQ2_K33.6 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.Axion 1.0 35BAxion · 35B (3.0B active)Q2_K15.8 GB—Won't run
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.Command R (08-2024) 32BCohere · 32BQ2_K15.8 GB—Won't run
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2 ChatDeepSeek · 236B (21.0B active)Q2_K96.4 GB—Won't run
42Fair quality (C) · 42 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.Apertus 70B InstructSwiss AI · 71BQ2_K32.5 GB—Won't run
42Fair quality (C) · 42 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.Aya Expanse 32BCohere · 32BQ2_K15.8 GB—Won't run
42Fair quality (C) · 42 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.Aya Vision 32BCohere · 33BQ2_K16.2 GB—Won't run
42Fair quality (C) · 42 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.OLMo 2 32B InstructAi2 · 32BQ2_K15.5 GB—Won't run
41Fair quality (C) · 41 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.NorthCUA Minibeipo-ai · 35B (3.0B active)Q2_K15.8 GB—Won't run
40Fair quality (C) · 40 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.Llama 3 70B InstructMeta · 71BQ2_K32.5 GB—Won't run
40Fair quality (C) · 40 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.Qwen2.5-Math 72B InstructAlibaba · 73BQ2_K32.0 GB—Won't run
39Basic quality (D) · 39 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.Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)Q2_K19.4 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_K59.7 GB—Won't run
37Basic quality (D) · 37 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.Command R 35B (v01)Cohere · 35BQ2_K26.3 GB—Won't run
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)Q2_K21.3 GB—Won't run
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 110B ChatAlibaba · 111BQ2_K48.7 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.Aya 23 35BCohere · 35BQ2_K26.3 GB—Won't run
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Grok-1 (314B)xAI · 314B (86.0B active)Q2_K129 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.Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)Q2_K22.3 GB—Won't run
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Mixtral 8x7B InstructMistral AI · 47B (12.9B active)Q2_K21.3 GB—Won't run
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)Q2_K25.0 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_K194 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.Yi 1.5 34B Chat01.AI · 34BQ2_K16.3 GB—Won't run
30Basic quality (D) · 30 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.Code Llama 70B InstructMeta · 69BQ2_K30.5 GB—Won't run
30Basic quality (D) · 30 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.DeepSeek Coder 33B InstructDeepSeek · 33BQ2_K17.0 GB—Won't run
30Basic quality (D) · 30 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.LLaVA 1.6 34BLLaVA · 35BQ2_K16.5 GB—Won't run
30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 32B ChatAlibaba · 33BQ2_K16.7 GB—Won't run
28Basic quality (D) · 28 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.DeepSeek LLM 67B ChatDeepSeek · 67BQ2_K30.1 GB—Won't run
28Basic quality (D) · 28 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.Granite Code 34B InstructIBM · 34BQ2_K15.4 GB—Won't run
28Basic quality (D) · 28 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.Yi 34B Chat01.AI · 34BQ2_K16.3 GB—Won't run
26Basic quality (D) · 26 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.Code Llama 34B InstructMeta · 34BQ2_K16.7 GB—Won't run
25Basic quality (D) · 25 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.Llama 2 70B ChatMeta · 69BQ2_K30.5 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_K73.7 GB—Won't run
11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking.Falcon 40B InstructTII · 42BQ2_K18.5 GB—Won't run

Image models on the AMD EPYC 7002 / 7003 series NAS (16 GB)

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 4BBlack Forest Labs · 3.9BFP810.2 GB37 sRuns well
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.FLUX 3 Image KleinBlack Forest Labs · 5.6BQ4 GGUF10.2 GB4.7 minVery slow
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Z-Image TurboAlibaba (Tongyi) · 6.2BQ4 GGUF10.1 GB2.1 minSlow
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Z-ImageAlibaba (Tongyi) · 6.2BQ4 GGUF10.1 GB14.0 minVery slow
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 9BBlack Forest Labs · 9.1BQ4 GGUF8.0 GB1.6 minSlowencoder unloaded after use
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-Image TurboBaidu · 8.0BFP810.6 GB2.1 minSlowtight fit · encoder unloaded after use
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-ImageBaidu · 8.0BQ8 GGUF11.2 GB18.2 minVery slowtight fit · encoder unloaded after use
81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.MOSS-Image SFTOpenMOSS · 5.1BQ8 GGUF7.8 GB11.6 minVery slowencoder unloaded after use
54Fair quality (C) · 54 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.SDXL-Lightning (4-step)ByteDance · 2.6BFP168.9 GB29 sRuns well
40Fair quality (C) · 40 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.SDXL TurboStability AI · 2.6BFP167.6 GB6.2 sRuns great
58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.DreamShaper XL v2 TurboLykon · 2.6BFP168.9 GB53 sSlow
62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Juggernaut XL v9RunDiffusion · 2.6BFP168.9 GB3.1 minVery slow
62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.RealVisXL V5.0SG161222 · 2.6BFP168.9 GB3.1 minVery slow
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Krea [dev]Black Forest Labs · 11.9BQ4 GGUF10.0 GB10.4 minVery slowencoder unloaded after use
60Good quality (B) · 60 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.Animagine XL 4.0Cagliostro Lab · 2.6BFP168.9 GB2.9 minVery slow
60Good quality (B) · 60 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.Illustrious XL v0.1OnomaAI · 2.6BFP168.9 GB2.9 minVery slow
74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [dev]Black Forest Labs · 11.9BNF49.5 GB9.5 minVery slowencoder unloaded after use
93Excellent quality (A+) · 93 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.Fibo 2.0 DevBria AI · 8.1BFP168.1 GB20.0 minVery slowCPU offload
58Good quality (B) · 58 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.Pony Diffusion V6 XLPurpleSmartAI · 2.6BFP168.9 GB2.6 minVery slow
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Krea 2 TurboKrea · 12.8BFP87.1 GB3.4 minVery slowCPU offload
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Lumina-Image 2.0Shanghai AI Lab · 2.6BFP87.5 GB4.3 minVery slow
60Good quality (B) · 60 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.Playground v2.5Playground AI · 2.6BFP168.9 GB5.1 minVery slow
72Great quality (A) · 72 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.Iris-3BSperidlabs · 3.0BFP168.4 GB11.5 minVery slowencoder unloaded after use
65Good quality (B) · 65 of 100: how capable the model is at NF4, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [schnell]Black Forest Labs · 11.9BNF49.5 GB1.6 minSlowencoder unloaded after use
64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.OmniGen2BAAI (VectorSpaceLab) · 4.0BFP810.3 GB9.9 minVery slowtight fit
72Great quality (A) · 72 of 100: how capable the model is at NF4, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Chroma1-HDLodestone Rock · 8.9BNF47.7 GB15.8 minVery slowencoder unloaded after use
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Ideogram 4Ideogram · 18.6BFP88.9 GB20.0 minVery slowCPU offload
56Good quality (B) · 56 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.Animagine XL 3.1Cagliostro Lab · 2.6BFP168.9 GB2.9 minVery slow
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Kontext [dev]Black Forest Labs · 11.9BQ4 GGUF10.6 GB19.0 minVery slowtight fit · encoder unloaded after use
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.KolorsKuaishou · 2.6BFP811.0 GB2.5 minVery slowtight fit
55Good quality (B) · 55 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.Stable Diffusion XL 1.0Stability AI · 2.6BFP168.9 GB3.1 minVery slow
68Good quality (B) · 68 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.CogView4 6BZhipu AI · 6.4BFP88.8 GB11.7 minVery slowencoder unloaded after use
50Fair quality (C) · 50 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.Stable Diffusion 3 MediumStability AI · 2.0BFP89.9 GB1.9 minSlow
56Good quality (B) · 56 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.Stable Diffusion 3.5 MediumStability AI · 2.5BFP810.4 GB3.7 minVery slowtight fit
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [dev]Black Forest Labs · 32.2BQ4 GGUF10.1 GB38.5 minVery slowCPU offload
52Fair quality (C) · 52 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.Hunyuan-DiT v1.2Tencent · 1.5BFP169.3 GB4.1 minVery slow
50Fair quality (C) · 50 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.Stable CascadeStability AI · 5.2BFP88.1 GB3.1 minVery slow
60Good quality (B) · 60 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.Stable Diffusion 3.5 Large TurboStability AI · 8.1BFP810.7 GB62 sSlowtight fit · encoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.AuraFlow v0.3fal · 6.9BQ4 GGUF7.7 GB11.5 minVery slow
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FullHiDream.ai · 17.1BQ8 GGUF9.3 GB46.1 minVery slowCPU offload
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.FireRed-Image-Edit 1.1rednote (FireRed Team) · 20.4BQ8 GGUF11.2 GB81.9 minVery slowtight fit · CPU offload
79Great quality (A) · 79 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 DevHiDream.ai · 17.1BQ8 GGUF9.3 GB17.4 minVery slowCPU offload
85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image-Edit 2511Alibaba · 20.4BQ8 GGUF11.2 GB81.9 minVery slowtight fit · CPU offload
61Good quality (B) · 61 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 LargeStability AI · 8.1BQ4 GGUF7.5 GB9.5 minVery slowencoder unloaded after use
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2512Alibaba · 20.4BQ4 GGUF10.4 GB1.6 hVery slowtight fit · CPU offload
75Great quality (A) · 75 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FastHiDream.ai · 17.1BQ8 GGUF9.3 GB10.2 minVery slowCPU offload
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Fill [dev]Black Forest Labs · 11.9BFP86.8 GB10.0 minVery slowCPU offload
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 · 3.0BFP168.7 GB6.5 minVery slowencoder unloaded after use
28Basic quality (D) · 28 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.SD TurboStability AI · 0.9BFP163.3 GB3.3 sRuns great
30Basic quality (D) · 30 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.LCM DreamShaper v7Tsinghua (LCM) · 0.9BFP162.8 GB10 sRuns great
42Fair quality (C) · 42 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.Realistic Vision V5.1SG161222 · 0.9BFP162.8 GB49 sSlow
40Fair quality (C) · 40 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.DreamShaper 8Lykon · 0.9BFP162.8 GB49 sSlow
50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.PixArt-Σ XL 1024PixArt · 0.6BFP163.3 GB65 sSlowencoder unloaded after use
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 1.5Stability AI / Runway · 0.9BFP162.8 GB49 sSlow
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.Cosmos3-Super Text2Image (64B)NVIDIA · 64.0BFP826.1 GB—Won't run
88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.HunyuanImage 3.0 (80B-A13B)Tencent · 83.0BFP832.8 GB—Won't run
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2.1Alibaba · 7.1BQ4 GGUF26.0 GB—Won't run
86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Qwen-ImageAlibaba · 20.4BFP813.3 GB—Won't run
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Ming-Image 0.1 DesignAnt Group (inclusionAI) · 6.2BFP816.4 GB—Won't run
82Great quality (A) · 82 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Qwen-Image 2.1 TurboAlibaba · 7.1BQ4 GGUF15.7 GB—Won't run

Video models on the AMD EPYC 7002 / 7003 series NAS (16 GB)

Quality Model Quant Memory Speed Runs
49Fair quality (C) · 49 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.LTX-Video 2BLightricks · 1.9BFP810.8 GB15.4 minSlowtight fit
83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Bernini-R A14B (video generation + editing)ByteDance · 14.3BFP810.7 GB9.6 hVery slowtight fit · CPU offload
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 2BZhipu AI · 1.7BFP811.0 GB37.0 minSlowtight fit
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.HY-OmniWeaving (8.3B, unified video)Tencent · 8.3BFP87.8 GB7.1 hVery slowCPU offload
55Good quality (B) · 55 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.Wan 2.1 T2V 1.3BAlibaba · 1.3BFP168.4 GB2.9 hVery slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5BZhipu AI · 5.0BFP89.6 GB1.9 hVery slowencoder unloaded after use
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 5B I2VZhipu AI · 5.6BFP810.2 GB1.9 hVery slowencoder unloaded after use
55Good quality (B) · 55 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.Wan 2.1 VACE 1.3BAlibaba · 2.2BFP1610.1 GB3.1 hVery slowencoder unloaded after use
70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3BQ4 GGUF9.0 GB17.8 hVery slowCPU offload
68Good quality (B) · 68 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 6.0 Video Lite (3B, video + audio)Sber AI · 3.2BFP168.9 GB4.6 hVery slowCPU offload
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9BFP810.8 GB5.3 hVery slowtight fit · CPU offload
73Great quality (A) · 73 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 480PAlibaba · 14.0BQ8 GGUF10.8 GB15.4 hVery slowtight fit · CPU offload
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4BFP811.0 GB3.2 hVery slowtight fit · encoder unloaded after use
35Basic quality (D) · 35 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.AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3BFP164.7 GB13.7 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
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.Kandinsky 6.0 Pro (29B, video + audio)Sber AI · 30.1BFP1627.8 GB—Won't run
83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.MiniMax H3 (33B, video + audio)MiniMax · 20.1BQ4 GGUF19.6 GB—Won't run
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo 1.5 (8.3B)Tencent · 8.3BFP823.9 GB—Won't run
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.LTX-2.5 (22B, video + audio)Lightricks · 21.0BQ4 GGUF16.8 GB—Won't run
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.LTX-2.3Lightricks · 18.9BQ4 GGUF16.4 GB—Won't run
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 I2V A14BAlibaba · 14.0BQ4 GGUF21.3 GB—Won't run
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 T2V A14BAlibaba · 14.0BQ4 GGUF21.3 GB—Won't run
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.SCAIL-2 14B (character animation)Zhipu AI · 16.4BFP812.5 GB—Won't run
76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 T2V 14B 720PSkywork · 14.0BFP826.0 GB—Won't run
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.LTX-2 (19B, video + audio)Lightricks · 18.9BQ4 GGUF16.4 GB—Won't run
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.Step-Video T2V (30B)StepFun · 30.0BFP825.0 GB—Won't run
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.Wan-Dancer 14B (music to dance)Alibaba · 17.3BFP835.6 GB—Won't run
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 720PAlibaba · 14.0BQ4 GGUF21.3 GB—Won't run
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 T2V 14BAlibaba · 14.0BQ4 GGUF21.3 GB—Won't run
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 VACE 14BAlibaba · 17.3BQ4 GGUF22.0 GB—Won't run
72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 Animate 14BAlibaba · 17.3BQ4 GGUF21.3 GB—Won't run
72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 T2V 14B 540PSkywork · 14.0BFP814.2 GB—Won't run
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Open-Sora 2.0 (11B)HPC-AI Tech · 11.0BFP1619.3 GB—Won't run
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Cosmos-Predict2 14B Video2WorldNVIDIA · 14.0BFP824.7 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo 13BTencent · 13.0BQ4 GGUF24.8 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.HunyuanVideo I2V 13BTencent · 13.0BQ4 GGUF24.8 GB—Won't run
66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.LTX-Video 13B 0.9.8 (distilled)Lightricks · 13.0BFP816.1 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 TI2V 5BAlibaba · 5.0BQ4 GGUF21.4 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Mochi 1 Preview (10B)Genmo · 10.0BFP814.7 GB—Won't run
60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Cosmos 1.0 Diffusion 7B Text2WorldNVIDIA · 7.0BFP1629.2 GB—Won't run
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 1.5 5BZhipu AI · 5.6BFP831.2 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Cosmos-Predict2 2B Video2WorldNVIDIA · 2.0BFP820.5 GB—Won't run
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Allegro (2.8B)Rhymes AI · 2.8BFP1624.7 GB—Won't run

Decision models on the AMD EPYC 7002 / 7003 series NAS (16 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 GB44 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 22MMeta · 71MQ8_00.7 GB103 msRuns great
80Great quality (A) · 80 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.GLiNER2.5 DecideFastino · 490MQ8_01.2 GB345 msRuns well
86Excellent quality (A+) · 86 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.Jina Reranker v3.5Jina AI · 600MQ8_02.4 GB780 msSlow
84Great quality (A) · 84 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 v3Jina AI · 600MQ8_02.4 GB780 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_06.1 GB5.2 sVery slow
66Good quality (B) · 66 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.GLiClass Base v3Knowledgator · 190MQ8_00.8 GB136 msRuns well
80Great quality (A) · 80 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.FRIDA-DecisionsSber AI · 820MQ8_01.7 GB574 msSlow
74Great quality (A) · 74 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.GLiClass ModernBERT Large v3Knowledgator · 400MQ8_01.1 GB282 msRuns well
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 GB129 msRuns great
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 GB213 msRuns well
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 GB394 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_06.1 GB5.2 sVery slow
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 8BAlibaba · 8.2BQ6_K8.6 GB10.6 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.Qwen3 Reranker 0.6BAlibaba · 600MQ8_02.4 GB780 msSlow
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 GB310 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.Granite Embedding Reranker English R2IBM · 150MQ8_00.8 GB213 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 GB150 msRuns well
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_05.9 GB5.0 sVery slow
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_06.4 GB3.0 sVery slow
90Excellent quality (A+) · 90 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.Skywork Reward V2 Llama 3.1 8BSkywork · 7.5BQ8_010.4 GB20.9 sVery slowtight fit
70Great quality (A) · 70 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.ModernBERT Large Zero-shot v2.0Moritz Laurer · 400MQ8_01.1 GB282 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_03.3 GB2.0 sVery slow
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.d1 3BLiquid AI · 3.1BQ8_04.9 GB2.0 sVery slow
76Great quality (A) · 76 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-base v2Mixedbread · 490MQ8_02.1 GB638 msSlow
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.GLiGuard 300MFastino · 210MQ8_00.9 GB296 msRuns well
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.LayaConvai Innovations · 420MQ8_01.2 GB296 msRuns well
80Great quality (A) · 80 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.zerank-1 smallZeroEntropy · 1.7BQ8_03.6 GB2.2 sVery slow
66Good quality (B) · 66 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.ProtectAI DeBERTa v3 Prompt Injection v2Protect AI · 180MQ8_00.8 GB254 msRuns well
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.Jina Reranker v2 Base MultilingualJina AI · 280MQ8_01.0 GB394 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 GB3.2 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 GB41 msRuns great
72Great quality (A) · 72 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.DuoGuard 0.5BDuoGuard · 490MQ8_01.2 GB686 msSlow
84Great quality (A) · 84 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.Skywork Reward V2 Qwen3 8BSkywork · 7.6BQ8_010.5 GB21.1 sVery slowtight fit
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_04.3 GB3.3 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 GB797 msSlow
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 GB227 msRuns well
85Excellent quality (A+) · 85 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.Qwen3Guard Gen 8BAlibaba · 8.2BQ6_K8.6 GB11.0 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_06.5 GB6.0 sVery slow
62Good quality (B) · 62 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.HHEM 2.1 OpenVectara · 110MQ8_00.7 GB310 msRuns well
62Good quality (B) · 62 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.GLiNER Multi v2.1Urchade Zaratiana · 290MQ8_01.0 GB206 msRuns well
72Great quality (A) · 72 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.Skywork Reward V2 Qwen3 0.6BSkywork · 600MQ8_01.4 GB1.7 sVery slow
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 8.0BQ6_K8.4 GB10.8 sVery slow
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Granite Guardian 4.1 8BIBM · 8.4BQ6_K8.8 GB11.2 sVery slow
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_02.6 GB1.0 sSlow
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_05.6 GB3.7 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.WildGuard 7BAi2 · 7.3BQ8_09.5 GB9.9 sVery slow
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Granite Guardian 3.3 8BIBM · 8.2BQ6_K8.6 GB11.0 sVery slow
56Good quality (B) · 56 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.BART Large MNLIMeta · 410MQ8_01.1 GB289 msRuns well
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_04.0 GB2.2 sVery slow
66Good quality (B) · 66 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.LettuceDetect LargeKR Labs · 400MQ8_01.1 GB1.1 sSlow
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_06.4 GB15.2 sVery slow
78Great quality (A) · 78 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.DynaGuard 8BUniversity of Maryland · 8.2BQ6_K8.6 GB24.0 sVery slow
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Selene 1 Mini 8BAtla · 8.0BQ6_K8.4 GB33.0 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_09.8 GB35.6 sVery slow
63Good quality (B) · 63 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.ShieldGemma 9BGoogle · 9.2BQ6_K9.8 GB11.9 sVery slow
67Good quality (B) · 67 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.Llama Guard 3 8BMeta · 8.0BQ6_K8.4 GB10.8 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_04.5 GB3.4 sVery slow
70Great quality (A) · 70 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.DynaGuard 1.7BUniversity of Maryland · 2.0BQ8_03.9 GB7.2 sVery slow
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.Llama Guard 4 12BMeta · 12BQ6_K11.8 GB16.1 sVery slowtight fit
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_03.2 GB2.1 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_09.5 GB33.8 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_06.4 GB17.8 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_06.4 GB17.8 sVery slow
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 20BOpenAI · 22B (3.6B active)MXFP413.9 GB9.8 sVery slowfar over memory limit
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 27BFastino · 26BQ8_034.8 GB—Won't run
81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.CompassJudger-2 32BOpenCompass · 33BQ4_K_M22.1 GB—Won't run
80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 120BOpenAI · 117B (5.1B active)MXFP468.2 GB—Won't run
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Prometheus 2 8x7BPrometheus Eval · 47B (13B active)Q4_K_M30.3 GB—Won't run
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 27BGoogle · 27BQ4_K_M18.9 GB—Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 352 of 619 LLMs run well on your AMD EPYC 7002 / 7003 series NAS (16 GB).

ASRock Intel Arc B570 Challenger 10GB OC Cheapest upgrade Intel Arc B570 10.0 GB · $219 launch price +32 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 +104 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 +194 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?