What the Intel Arc A580 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.

VRAM
8.0 GB
Usable for models
8.0 GB
Memory bandwidth
512 GB/s
FP16 compute
24.6 TFLOPS
458 / 619 LLMs run Best: K2 Horizon 7B (A) 49 / 60 Image models run Best: FLUX.2 [klein] 4B (A) 7 / 43 Video models run Best: LTX-Video 2B (C) 65 / 70 Decision models run Best: Jina Reranker v3.5 (A+)

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

LLMs on the Intel Arc A580

Quality Model Quant Memory Speed Runs
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.K2 Horizon 7BInstitute of Foundation Models · 9.0BQ4_K_M7.7 GB53.3 tok/sRuns welltight fit
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.MiMo V2.6 Distill Qwen 9BXiaomi · 9.4BQ5_K_M7.9 GB42.1 tok/sRuns welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.SenseNova Loop 9B PreviewSenseTime · 9.7BQ4_K_M7.4 GB49.7 tok/sRuns welltight fit
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.5 9BDeepReinforce · 9.7BQ4_K_M7.2 GB49.8 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 86/100 (quality, fit, speed and memory use) sets the ranking.TMax 9BAi2 · 9.0BQ4_K_M6.7 GB53.6 tok/sRuns great
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 9BAlibaba · 9.7BQ4_K_M7.2 GB49.8 tok/sRuns welltight fit
71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Ornith 1.0 9BDeepReinforce · 9.7BQ4_K_M7.2 GB49.8 tok/sRuns welltight fit
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.Nemotron Labs Dory 1.0 4BNVIDIA · 4.0BQ8_05.7 GB61.4 tok/sRuns great
69Good quality (B) · 69 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 12BGoogle · 12BQ3_K_M7.5 GB51.9 tok/sRuns welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Nanbeige4.2 3BBOSS Zhipin (Nanbeige) · 4.2BQ6_K5.9 GB79.9 tok/sRuns great
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3.5 Bolt E4BNVIDIA · 8.0BQ6_K7.7 GB74.0 tok/sRuns welltight fit
66Good quality (B) · 66 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.Spark-X2.6 4BSparkLLM · 4.1BQ8_05.7 GB59.5 tok/sRuns great
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.UI-Mate 9BTencent · 9.4BQ5_K_M7.9 GB42.1 tok/sRuns welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.UI-Venus 2 9BAnt Group (inclusionAI) · 9.4BQ5_K_M7.9 GB42.1 tok/sRuns welltight fit
67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.Gemma 4 E4BGoogle · 8.0BQ6_K7.7 GB74.0 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 83/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 8BIBM · 8.8BQ4_K_M7.7 GB54.6 tok/sRuns welltight fit
62Good quality (B) · 62 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.Gemma 4 E2BGoogle · 5.1BQ8_06.5 GB106 tok/sRuns great
62Good quality (B) · 62 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.Qwen3.5 4BAlibaba · 4.7BQ8_06.2 GB52.4 tok/sRuns great
61Good quality (B) · 61 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.TMax 4BAi2 · 4.2BQ8_05.7 GB58.1 tok/sRuns great
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.Agents-A1 4BInternScience · 4.5BQ8_06.1 GB53.8 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 2BOpenBMB · 2.5BF166.4 GB44.7 tok/sRuns great
59Good quality (B) · 59 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.Mage-VL-Cowork 4.7BMicrosoft · 4.7BQ6_K6.1 GB70.3 tok/sRuns great
58Good quality (B) · 58 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.Fara 1.5 4BMicrosoft · 4.5BQ8_06.1 GB53.8 tok/sRuns great
59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Ling 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI) · 7.9B (1.3B active)Q6_K7.7 GB133 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 80/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Nano 9B v2NVIDIA · 8.9BQ4_K_M6.6 GB54.0 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 0528 Qwen3 8BDeepSeek · 8.2BQ4_K_M7.2 GB58.6 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 80/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 8BShanghai AI Lab · 8.5BQ4_K_M7.4 GB56.3 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 80/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 8B InstructAlibaba · 8.8BQ4_K_M7.6 GB54.7 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 80/100 (quality, fit, speed and memory use) sets the ranking.Mellum2.1 Thinking (12B-A2.5B)JetBrains · 12B (2.5B active)Q3_K_M7.1 GB138 tok/sRuns welltight fit
56Good quality (B) · 56 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.Qwen3 4B Thinking 2507Alibaba · 4.0BQ8_06.5 GB60.8 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Mage-VL 4.7BMicrosoft · 4.7BQ6_K6.1 GB70.3 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.GLM-4.1V 9B ThinkingZhipu AI · 10BQ4_K_M7.6 GB46.7 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 79/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 8BIBM · 8.8BQ4_K_M7.7 GB54.6 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 79/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.5 8BOpenBMB · 8.7BQ4_K_M7.5 GB55.2 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 79/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 8BAlibaba · 8.2BQ4_K_M7.2 GB58.6 tok/sRuns welltight fit
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1R 7BTII · 7.6BQ5_K_M6.8 GB52.3 tok/sRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Seed-Coder 8B ReasoningByteDance · 8.3BQ5_K_M7.9 GB48.1 tok/sRuns welltight fit
54Fair quality (C) · 54 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.Qwen3 4B Instruct 2507Alibaba · 4.0BQ8_06.5 GB60.8 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 4B InstructAlibaba · 4.4BQ6_K5.8 GB75.0 tok/sRuns great
55Good quality (B) · 55 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.InternVL3 8BShanghai AI Lab · 7.9BQ6_K8.0 GB42.0 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 78/100 (quality, fit, speed and memory use) sets the ranking.GLM-Z1 9B (0414)Zhipu AI · 9.4BQ4_K_M7.1 GB51.1 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 78/100 (quality, fit, speed and memory use) sets the ranking.MiMo-VL 7B RLXiaomi · 8.3BQ4_K_M7.3 GB57.8 tok/sRuns welltight fit
52Fair quality (C) · 52 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.Qwen2.5 Coder 7B InstructAlibaba · 7.6BQ4_K_M6.1 GB63.0 tok/sRuns great
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.EXAONE Deep 7.8BLG AI Research · 7.8BQ5_K_M7.6 GB50.7 tok/sRuns welltight fit
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.MiMo 7B RLXiaomi · 7.8BQ5_K_M7.8 GB50.7 tok/sRuns welltight fit
54Fair quality (C) · 54 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Seed-Coder 8B InstructByteDance · 8.3BQ5_K_M7.9 GB48.1 tok/sRuns welltight fit
52Fair quality (C) · 52 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 3BIBM · 3.7BQ8_05.6 GB66.8 tok/sRuns great
56Good quality (B) · 56 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.LFM3 1.7BLiquid AI · 1.7BF164.6 GB65.1 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM4 8BOpenBMB · 8.2BQ4_K_M6.3 GB58.6 tok/sRuns great
51Fair quality (C) · 51 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.OpenReasoning Nemotron 7BNVIDIA · 7.6BQ4_K_M6.1 GB63.0 tok/sRuns great
53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Ministral 3 8BMistral AI · 8.9BQ4_K_M7.6 GB53.8 tok/sRuns welltight fit
52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Nano 8B v1NVIDIA · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
52Fair quality (C) · 52 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3 7B ThinkAi2 · 7.3BQ5_K_M7.7 GB54.3 tok/sRuns welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Nano 4BNVIDIA · 4.0BQ8_05.3 GB61.6 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 4BAlibaba · 4.0BQ8_06.5 GB60.8 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qianfan-OCR 4BBaidu · 4.7BQ6_K6.1 GB70.3 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 7B InstructTencent · 7.5BQ4_K_M6.6 GB64.0 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 8B-A1BLiquid AI · 8.5B (1.5B active)Q4_K_M6.3 GB154 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-o 2.6 8BOpenBMB · 8.7BQ4_K_M6.8 GB55.4 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B InstructAlibaba · 7.6BQ4_K_M6.1 GB63.0 tok/sRuns great
49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 7B InstructAlibaba · 8.3BQ4_K_M6.5 GB57.9 tok/sRuns great
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 7B InstructTII · 7.6BQ5_K_M6.8 GB52.3 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.LFM3-VL 2BLiquid AI · 1.9BF164.9 GB58.7 tok/sRuns great
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Foundation-Sec 8B ReasoningCisco Foundation AI · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Nanobeipo-ai · 9.4BQ5_K_M7.9 GB42.1 tok/sRuns welltight fit
50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 12B ITGoogle · 12BQ3_K_M7.6 GB50.9 tok/sRuns welltight fit
48Fair quality (C) · 48 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.LightOnOCR-3 4BLightOn · 4.5BQ8_06.1 GB53.8 tok/sRuns great
47Fair quality (C) · 47 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.Chandra OCR 2Datalab · 5.3BQ6_K5.6 GB62.9 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Fara 7BMicrosoft · 8.3BQ4_K_M6.5 GB57.9 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 9BFastino · 7.9BQ4_K_M6.1 GB60.5 tok/sRuns great
47Fair quality (C) · 47 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.InternLM3 8B InstructShanghai AI Lab · 8.8BQ4_K_M6.8 GB54.6 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 7B Instruct 1MAlibaba · 7.6BQ4_K_M6.1 GB63.0 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.GLM-4 9B 0414Zhipu AI · 9.4BQ4_K_M7.1 GB51.1 tok/sRuns welltight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Llama 8BDeepSeek · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Foundation-Sec 1.1 8B InstructCisco Foundation AI · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.InternVL2.5 8BShanghai AI Lab · 8.1BQ5_K_M7.8 GB49.1 tok/sRuns welltight fit
48Fair quality (C) · 48 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3 7B InstructAi2 · 7.3BQ5_K_M7.7 GB54.3 tok/sRuns welltight fit
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.1 3BIBM · 3.4BQ8_05.3 GB71.9 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Mini Reasoning (3.8B)Microsoft · 3.8BQ8_06.1 GB63.6 tok/sRuns great
45Fair quality (C) · 45 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 2.6 8BOpenBMB · 8.1BQ4_K_M6.4 GB59.3 tok/sRuns great
45Fair quality (C) · 45 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 4B ITGoogle · 4.3BQ8_05.8 GB56.8 tok/sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3n E4BGoogle · 7.9BQ5_K_M6.7 GB99.2 tok/sRuns great
44Fair quality (C) · 44 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.WeVisOne-VL 4BTencent · 4.8BQ6_K6.2 GB69.0 tok/sRuns great
46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Hermes 3 (Llama 3.1 8B)Nous Research · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
46Fair quality (C) · 46 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 8B InstructMeta · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
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.LFM2.5 2.6BLiquid AI · 2.7BF166.5 GB41.7 tok/sRuns great
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.MedGemma 4B ITGoogle · 4.3BQ8_05.8 GB56.8 tok/sRuns great
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.Ministral 3 3BMistral AI · 3.9BQ8_06.0 GB63.5 tok/sRuns great
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.Phi-4 Mini (3.8B)Microsoft · 3.8BQ8_06.1 GB63.6 tok/sRuns great
46Fair quality (C) · 46 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.Ministral 3 14B ReasoningMistral AI · 14BQ2_K7.9 GB56.5 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 74/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 7BDeepSeek · 7.6BQ4_K_M6.1 GB63.0 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 7B InstructTII · 7.5BQ4_K_M6.5 GB64.4 tok/sRuns great
43Fair quality (C) · 43 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 4.0 H Tiny (7B-A1B)IBM · 6.9B (1.0B active)Q6_K6.8 GB151 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Nano 4B v1.1NVIDIA · 4.5BQ6_K5.8 GB73.9 tok/sRuns great
43Fair quality (C) · 43 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.Phi-4 Multimodal InstructMicrosoft · 5.6BQ6_K6.6 GB59.8 tok/sRuns great
45Fair quality (C) · 45 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 9B Chat (2024)Zhipu AI · 9.4BQ4_K_M7.1 GB51.1 tok/sRuns welltight fit
45Fair quality (C) · 45 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 9B Chat 1MZhipu AI · 9.5BQ4_K_M7.5 GB50.6 tok/sRuns welltight fit
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.Unlimited OCR 2 (3B-A0.6B)Baidu · 3.3B (0.6B active)Q8_05.0 GB160 tok/sRuns great
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.Ministral 3 14BMistral AI · 14BQ2_K7.9 GB56.5 tok/sRuns welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.DeepHermes 3 Llama 3 8B PreviewNous Research · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 Llama 3.1 8BCognitive Computations · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 7.8BLG AI Research · 7.8BQ5_K_M7.6 GB50.7 tok/sRuns welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Ministral 8B (2410)Mistral AI · 8.0BQ5_K_M7.9 GB49.5 tok/sRuns welltight fit
44Fair quality (C) · 44 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Tülu 3 8BAi2 · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 4B InstructTencent · 4.2BQ8_06.7 GB57.9 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Aya Vision 8BCohere · 8.6BQ4_K_M6.6 GB55.6 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Command R7BCohere · 8.0BQ4_K_M6.3 GB59.8 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Small 8K InstructMicrosoft · 7.4BQ4_K_M6.6 GB65.0 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 7B InstructAlibaba · 7.6BQ4_K_M6.1 GB63.0 tok/sRuns great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 7B InstructAlibaba · 8.3BQ4_K_M6.5 GB57.9 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Apertus v1.5 8BSwiss AI · 8.9BQ4_K_M7.5 GB53.9 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 73/100 (quality, fit, speed and memory use) sets the ranking.CodeGeeX4 All 9BZhipu AI · 9.4BQ4_K_M7.1 GB51.1 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 73/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 8B InstructIBM · 8.2BQ4_K_M7.3 GB58.8 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 73/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 8BIBM · 8.2BQ4_K_M7.3 GB58.8 tok/sRuns welltight fit
43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 10B InstructTII · 10BQ3_K_M7.4 GB60.2 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 73/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9.4 Llama 3.1 8BCognitive Computations · 8.0BQ5_K_M7.8 GB49.4 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 73/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Llama 3 8BNous Research · 8.0BQ5_K_M7.8 GB49.4 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 73/100 (quality, fit, speed and memory use) sets the ranking.InternVL2 8BShanghai AI Lab · 8.1BQ5_K_M7.8 GB49.1 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 73/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.6 8BOpenChat · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.AFM 4.5BArcee AI · 4.6BQ8_06.5 GB52.9 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 Micro (3B)IBM · 3.4BQ8_05.3 GB71.9 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.Qwen3.5 2BAlibaba · 2.3BF165.6 GB49.6 tok/sRuns great
44Fair quality (C) · 44 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.North Micro VisionCohere · 2.5BQ8_04.6 GB98.6 tok/sRuns great
39Basic quality (D) · 39 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.Command R7B ArabicCohere · 8.0BQ4_K_M6.3 GB59.8 tok/sRuns great
42Fair quality (C) · 42 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.SmolLM3 3BHugging Face · 3.1BQ8_04.9 GB79.4 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Kimi-VL A3B Thinking 2506Moonshot AI · 16B (3.0B active)Q2_K7.8 GB144 tok/sRuns welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 9B ITGoogle · 9.2BQ3_K_M7.1 GB67.2 tok/sRuns welltight fit
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 8B InstructIBM · 8.2BQ4_K_M7.3 GB58.8 tok/sRuns welltight fit
44Fair quality (C) · 44 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.LFM2.5-VL 3BLiquid AI · 3.1BQ8_04.4 GB78.3 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Unlimited OCR (3B-A0.6B)Baidu · 3.3B (0.6B active)Q8_05.0 GB160 tok/sRuns great
88Excellent quality (A+) · 88 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.Qwen3.6 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.7 35B-A3BOpenBMB · 35B (3.0B active)Q4_K_M22.6 GB32.9 tok/sSlowheavy RAM offload
44Fair quality (C) · 44 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.Jamba Reasoning 3BAI21 Labs · 3.2BQ8_04.4 GB76.4 tok/sRuns great
38Basic quality (D) · 38 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-Omni 7BAlibaba · 11BQ3_K_M6.7 GB57.8 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Llama 3 8B InstructMeta · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 35B-A3BAlibaba · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 8B InstructIBM · 8.2BQ4_K_M6.7 GB58.8 tok/sRuns great
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 7B ChatShanghai AI Lab · 7.7BQ4_K_M6.8 GB62.0 tok/sRuns great
38Basic quality (D) · 38 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.Phi-3.5 Mini InstructMicrosoft · 3.8BQ4_K_M6.6 GB126 tok/sRuns great
38Basic quality (D) · 38 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.MiniCPM3 4BOpenBMB · 4.1BQ8_05.6 GB60.1 tok/sRuns great
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.TMax 2BAi2 · 1.9BF164.9 GB59.9 tok/sRuns great
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Mistral-NeMo-Minitron 8B InstructNVIDIA · 8.4BQ4_K_M7.5 GB57.1 tok/sRuns welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Nex N2 Mini (35B-A3B)Nex-AGI · 35B (3.0B active)Q4_K_M22.6 GB33.0 tok/sSlowheavy RAM offload
85Excellent quality (A+) · 85 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.Flint (40B-A2.5B)Recursive · 40B (2.5B active)Q4_K_M25.5 GB37.2 tok/sSlowheavy RAM offload
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.TeleOCRXingChen-AGI · 1.4BF164.8 GB79.3 tok/sRuns great
37Basic quality (D) · 37 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.S5 nanoMaritaca AI · 4.7BQ8_06.2 GB52.4 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Falcon3 Mamba 7B InstructTII · 7.3BQ5_K_M6.2 GB54.6 tok/sRuns great
86Excellent quality (A+) · 86 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.KAT-Coder V2.5 Dev (35B-A3B)Kuaishou · 35B (3.0B active)Q4_K_M22.3 GB33.1 tok/sSlowheavy RAM offload
86Excellent quality (A+) · 86 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.Sage-A1.5 35B-A3BInternScience · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
87Excellent quality (A+) · 87 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 4 26B-A4BGoogle · 26B (3.8B active)Q4_K_M17.1 GB29.7 tok/sSlowheavy RAM offload
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Apertus 8B InstructSwiss AI · 8.1BQ5_K_M7.8 GB49.3 tok/sRuns welltight fit
38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 8BCohere · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
36Basic quality (D) · 36 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.EXAONE 3.0 7.8B InstructLG AI Research · 7.8BQ4_K_M6.3 GB61.4 tok/sRuns great
36Basic quality (D) · 36 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.LFM2 8B-A1BLiquid AI · 8.3B (1.5B active)Q4_K_M6.2 GB154 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Mistral 7B Instruct v0.3Mistral AI · 7.3BQ4_K_M6.5 GB66.2 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 Vision InstructMicrosoft · 4.2BQ4_K_M6.8 GB116 tok/sRuns great
36Basic quality (D) · 36 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.Zamba2 7B InstructZyphra · 7.4BQ4_K_M6.3 GB65.2 tok/sRuns great
36Basic quality (D) · 36 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.Phi-3 Mini 4K InstructMicrosoft · 3.8BQ8_06.7 GB64.0 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 2B InstructAlibaba · 2.1BF166.2 GB52.9 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.Yi Coder 9B Chat01.AI · 8.8BQ4_K_M7.2 GB54.4 tok/sRuns welltight fit
42Fair quality (C) · 42 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.Jamba2 3BAI21 Labs · 3.0BQ8_04.2 GB80.7 tok/sRuns great
85Excellent quality (A+) · 85 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.Ornith 1.5 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
35Basic quality (D) · 35 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.Gemma 3n E2BGoogle · 5.4BQ6_K5.6 GB167 tok/sRuns great
35Basic quality (D) · 35 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.Voxtral Mini 3BMistral AI · 4.7BQ6_K5.8 GB71.2 tok/sRuns great
35Basic quality (D) · 35 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 3B InstructMeta · 3.2BQ8_05.3 GB76.1 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Codestral Mamba 7BMistral AI · 7.3BQ5_K_M6.2 GB54.4 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 7B InstructAlibaba · 7.6BQ5_K_M6.6 GB52.0 tok/sRuns great
84Great quality (A) · 84 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.Apodex 1.1 Mini (35B-A3B)Apodex · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
84Great quality (A) · 84 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.Ornith 1.0 35B-A3BDeepReinforce · 36B (3.0B active)Q4_K_M23.1 GB32.7 tok/sSlowheavy RAM offload
36Basic quality (D) · 36 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 2.9 Llama 3 8BCognitive Computations · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
83Great quality (A) · 83 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.GLM-4.7 Flash (30B-A3B)Zhipu AI · 31B (3.0B active)Q4_K_M20.5 GB33.8 tok/sSlowheavy RAM offload
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Hermes 2 Pro Mistral 7BNous Research · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Mini 128K InstructMicrosoft · 3.8BQ4_K_M6.6 GB126 tok/sRuns great
34Basic quality (D) · 34 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.Starling LM 7B BetaNexusflow · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 9B Chat01.AI · 8.8BQ4_K_M6.8 GB54.4 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 Lite (16B)DeepSeek · 16B (2.4B active)Q2_K7.5 GB162 tok/sRuns welltight fit
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Ling Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI) · 16B (1.4B active)Q2_K7.8 GB204 tok/sRuns welltight fit
36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Mistral Nemo 12B InstructMistral AI · 12BQ2_K7.2 GB64.6 tok/sRuns welltight fit
34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.LFM2 2.6BLiquid AI · 2.6BF166.3 GB43.8 tok/sRuns great
34Basic quality (D) · 34 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 3B InstructAlibaba · 3.8BQ8_05.3 GB65.2 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 9B V2LLM4Binary · 8.8BQ4_K_M7.2 GB54.4 tok/sRuns welltight fit
40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-V 4.7 1BOpenBMB · 1.6BF164.2 GB72.7 tok/sRuns great
33Basic quality (D) · 33 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.OpenChat 3.5 (0106)OpenChat · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
38Basic quality (D) · 38 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.Granite 4.0 H MicroIBM · 3.2BQ8_04.4 GB76.6 tok/sRuns great
35Basic quality (D) · 35 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.Llama 3.2 11B Vision InstructMeta · 11BQ3_K_M7.6 GB58.2 tok/sRuns welltight fit
82Great quality (A) · 82 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.Qwen AgentWorld 35B-A3BAlibaba · 35B (3.0B active)Q4_K_M22.3 GB33.1 tok/sSlowheavy RAM offload
82Great quality (A) · 82 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.Agents-A1 35B-A3BInternScience · 35B (3.0B active)Q4_K_M22.6 GB33.0 tok/sSlowheavy RAM offload
35Basic quality (D) · 35 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.Kimi-VL A3B InstructMoonshot AI · 16B (3.0B active)Q2_K7.8 GB144 tok/sRuns welltight fit
35Basic quality (D) · 35 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.Pixtral 12B (2409)Mistral AI · 12BQ2_K7.3 GB63.6 tok/sRuns welltight fit
42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM-OCR 1.0 1.3BOpenBMB · 1.3BF163.7 GB86.6 tok/sRuns great
32Basic quality (D) · 32 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.Mathstral 7BMistral AI · 7.3BQ4_K_M6.5 GB66.2 tok/sRuns great
32Basic quality (D) · 32 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 7B Instruct v0.2Mistral AI · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mistral 7B DPONous Research · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.OpenChat 3.5 (1210)OpenChat · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Vision 128K InstructMicrosoft · 4.2BQ4_K_M6.8 GB116 tok/sRuns great
36Basic quality (D) · 36 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.Falcon-H1 3B InstructTII · 3.2BQ8_04.6 GB77.6 tok/sRuns great
36Basic quality (D) · 36 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.Qwen2.5 Coder 3B InstructAlibaba · 3.1BQ8_04.6 GB79.1 tok/sRuns great
32Basic quality (D) · 32 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.Hermes 3 Llama 3.2 3BNous Research · 3.2BQ8_05.3 GB76.1 tok/sRuns great
34Basic quality (D) · 34 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.OLMo 2 7B InstructAi2 · 7.3BQ4_K_M7.6 GB65.8 tok/sRuns welltight fit
33Basic quality (D) · 33 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.Nous Hermes 2 SOLAR 10.7BNous Research · 11BQ3_K_M7.1 GB57.8 tok/sRuns welltight fit
33Basic quality (D) · 33 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.SOLAR 10.7B InstructUpstage · 11BQ3_K_M7.1 GB57.8 tok/sRuns welltight fit
80Great quality (A) · 80 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.Hunyuan Hy-Memory 30B-A3BTencent · 30B (3.0B active)Q4_K_M20.1 GB33.6 tok/sSlowheavy RAM offload
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Aya 23 8BCohere · 8.0BQ5_K_M7.8 GB49.4 tok/sRuns welltight fit
32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.RecurrentGemma 9B ITGoogle · 9.6BQ5_K_M7.9 GB41.2 tok/sRuns welltight fit
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 7BShanghai AI Lab · 7.7BQ4_K_M6.8 GB62.0 tok/sRuns great
30Basic quality (D) · 30 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.OpenHermes 2.5 Mistral 7BTeknium · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Starling LM 7B AlphaBerkeley · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
83Great quality (A) · 83 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.Raon-1 mini Preview (30B-A4B)KRAFTON · 29B (4.3B active)Q4_K_M18.6 GB25.8 tok/sSlowheavy RAM offload
34Basic quality (D) · 34 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.Qwen2.5 3B InstructAlibaba · 3.1BQ8_04.6 GB79.1 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 3.5 2.4BLG AI Research · 2.4BF166.4 GB46.7 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.2 2B InstructIBM · 2.5BF166.7 GB44.5 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.3 2BIBM · 2.5BF166.7 GB44.5 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 1.7BAlibaba · 2.0BF166.0 GB55.5 tok/sRuns great
32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Moonlight 16B-A3B InstructMoonshot AI · 16B (3.0B active)Q2_K7.6 GB144 tok/sRuns welltight fit
32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Phi-3 Medium (14B)Microsoft · 14BQ2_K7.4 GB56.5 tok/sRuns welltight fit
30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 3B InstructTII · 3.2BQ8_05.2 GB75.7 tok/sRuns great
29Basic quality (D) · 29 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.Qwen2.5-Omni 3BAlibaba · 5.5BQ6_K5.8 GB60.1 tok/sRuns great
29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Falcon Mamba 7B InstructTII · 7.3BQ5_K_M6.2 GB54.6 tok/sRuns great
31Basic quality (D) · 31 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 8B Instruct (128K)IBM · 8.1BQ5_K_M7.9 GB49.3 tok/sRuns welltight fit
28Basic quality (D) · 28 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 7B Instruct v0.1Mistral AI · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.PaddleOCR-VL 1.6 0.9BBaidu · 1.0BF163.1 GB117 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 2BGoogle · 2.6BF166.7 GB43.2 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 2B InstructIBM · 2.5BF166.7 GB44.5 tok/sRuns great
27Basic quality (D) · 27 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.Yi 1.5 6B Chat01.AI · 6.1BQ6_K6.2 GB55.0 tok/sRuns great
77Great quality (A) · 77 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.Laguna XS 2.1 (33B-A3B)Poolside · 33B (3.0B active)Q4_K_M22.7 GB31.7 tok/sSlowheavy RAM offload
76Great quality (A) · 76 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.North Mini Code 1.0 (30B-A3B)Cohere · 30B (3.0B active)Q4_K_M19.9 GB34.4 tok/sSlowheavy RAM offload
26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 Mistral 7BLLaVA · 7.6BQ4_K_M6.7 GB63.4 tok/sRuns great
26Basic quality (D) · 26 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.Neural Chat 7B v3.3Intel · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 2B InstructIBM · 2.6BF166.6 GB42.8 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Prover V2 7BDeepSeek · 6.9BQ2_K7.8 GB114 tok/sRuns welltight fit
28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2 Lite ChatDeepSeek · 16B (2.4B active)Q2_K7.5 GB162 tok/sRuns welltight fit
25Basic quality (D) · 25 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.OLMoE 1B-7B InstructAi2 · 6.9B (1.3B active)Q5_K_M6.5 GB148 tok/sRuns great
76Great quality (A) · 76 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.Nemotron Cascade 2 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M20.3 GB30.0 tok/sSlowheavy RAM offload
24Basic quality (D) · 24 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.WizardMath 7B v1.1WizardLM · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
24Basic quality (D) · 24 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.Zephyr 7B BetaHugging Face · 7.2BQ4_K_M6.5 GB66.3 tok/sRuns great
36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.MiniCPM5 1BOpenBMB · 1.1BF163.4 GB104 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen2-VL 2B InstructAlibaba · 2.2BF165.7 GB51.0 tok/sRuns great
26Basic quality (D) · 26 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.Granite Vision 3.2 2BIBM · 3.0BQ8_04.8 GB82.0 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.DeepScaleR 1.5B PreviewAgentica · 1.8BF164.8 GB63.3 tok/sRuns great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 30B-A3B Thinking 2507Alibaba · 31B (3.3B active)Q4_K_M20.4 GB30.7 tok/sSlowheavy RAM offload
74Great quality (A) · 74 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.Qwen3 Coder 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M20.4 GB30.7 tok/sSlowheavy RAM offload
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss 20BOpenAI · 21B (3.6B active)MXFP413.1 GB39.9 tok/sSlowheavy RAM offload
23Basic quality (D) · 23 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.StarCoder2 7BBigCode · 7.2BQ5_K_M6.6 GB55.3 tok/sRuns great
30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.EXAONE 4.0 1.2BLG AI Research · 1.3BF164.1 GB88.0 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.SmolVLM2 2.2B InstructHugging Face · 2.3BQ8_05.0 GB109 tok/sRuns great
27Basic quality (D) · 27 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.WeVisOne VL 2BTencent · 2.4BQ8_04.5 GB100 tok/sRuns great
73Great quality (A) · 73 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.Qwen3 30B-A3B Instruct 2507Alibaba · 31B (3.3B active)Q4_K_M20.4 GB30.7 tok/sSlowheavy RAM offload
92Excellent quality (A+) · 92 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.Qwen3.8 27BAlibaba · 28BQ5_K_M21.3 GB3.3 tok/sSlowheavy RAM offload
74Great quality (A) · 74 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.DiffusionGemma 26B-A4B ITGoogle · 26B (4.0B active)Q4_K_M17.2 GB28.4 tok/sSlowheavy RAM offload
73Great quality (A) · 73 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.Nemotron 3 Nano 30B-A3BNVIDIA · 32B (3.5B active)Q4_K_M20.3 GB30.0 tok/sSlowheavy RAM offload
22Basic quality (D) · 22 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.Nemotron Mini 4B InstructNVIDIA · 4.2BQ8_06.0 GB58.3 tok/sRuns great
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Zamba2 2.7B InstructZyphra · 2.7BF166.7 GB42.3 tok/sRuns great
23Basic quality (D) · 23 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.DeepSeek Coder 6.7B InstructDeepSeek · 6.7BQ2_K8.0 GB117 tok/sRuns welltight fit
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan 1.8B InstructTencent · 1.8BF165.1 GB62.9 tok/sRuns great
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 30B-A3B ThinkingAlibaba · 31B (3.3B active)Q4_K_M20.8 GB30.5 tok/sSlowheavy RAM offload
23Basic quality (D) · 23 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.StableLM 2 12B ChatStability AI · 12BQ3_K_M7.8 GB51.1 tok/sRuns welltight fit
91Excellent quality (A+) · 91 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.6 27BAlibaba · 28BQ5_K_M21.3 GB3.3 tok/sSlowheavy RAM offload
32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 1.2B InstructLiquid AI · 1.2BF163.4 GB96.3 tok/sRuns great
22Basic quality (D) · 22 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.SmolVLM 2.2B InstructHugging Face · 2.3BQ8_05.0 GB109 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 1.5B InstructAlibaba · 1.5BF164.3 GB73.1 tok/sRuns great
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 1.5B InstructTII · 1.6BF164.3 GB72.7 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H 1BIBM · 1.5BF164.0 GB77.2 tok/sRuns great
22Basic quality (D) · 22 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.LLM4Decompile 6.7B V2LLM4Binary · 6.7BQ2_K8.0 GB117 tok/sRuns welltight fit
90Excellent quality (A+) · 90 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.Nanbeige4.3 33BBOSS Zhipin (Nanbeige) · 33BQ4_K_M22.9 GB3.2 tok/sSlowheavy RAM offload
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.SmolLM2 1.7B InstructHugging Face · 1.7BF166.0 GB65.9 tok/sRuns great
20Basic quality (D) · 20 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.Stable Code Instruct 3BStability AI · 2.8BQ8_06.7 GB87.3 tok/sRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 27BAlibaba · 28BQ5_K_M21.3 GB3.3 tok/sSlowheavy RAM offload
66Good quality (B) · 66 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.Sarvam 30BSarvam AI · 32B (2.4B active)Q4_K_M20.8 GB41.3 tok/sSlowheavy RAM offload
19Basic quality (D) · 19 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.Granite Code 3B Instruct (128K)IBM · 3.5BQ6_K6.5 GB95.7 tok/sRuns great
19Basic quality (D) · 19 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.Yi 6B Chat01.AI · 6.1BQ6_K6.2 GB55.0 tok/sRuns great
70Great quality (A) · 70 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.Qwen3 30B-A3BAlibaba · 31B (3.3B active)Q4_K_M20.4 GB30.7 tok/sSlowheavy RAM offload
70Great quality (A) · 70 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.Qwen3-VL 30B-A3B InstructAlibaba · 31B (3.3B active)Q4_K_M20.8 GB30.5 tok/sSlowheavy RAM offload
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 1.5BDeepSeek · 1.8BF164.8 GB63.3 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.d1 2BLiquid AI · 1.9BF164.9 GB58.7 tok/sRuns great
68Good quality (B) · 68 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.Nemotron 3.5 Lightning 30B-A3BNVIDIA · 32B (3.0B active)Q4_K_M20.3 GB34.4 tok/sSlowheavy RAM offload
21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 7BMicrosoft · 6.7BQ5_K_M7.9 GB58.8 tok/sRuns welltight fit
20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.1 3B-A800M InstructIBM · 3.3B (0.8B active)Q8_05.0 GB141 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.SQLCoder 7B v2Defog · 6.7BQ2_K8.0 GB117 tok/sRuns welltight fit
89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Muse Glimmer 30BMeta · 30BQ5_K_M22.3 GB3.1 tok/sSlowheavy RAM offload
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.LFM2.5 24B-A2BLiquid AI · 24B (2.5B active)Q2_K10.8 GB94.5 tok/sRuns welloffloads to RAM
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 1.5B InstructAlibaba · 1.5BF164.3 GB73.1 tok/sRuns great
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 1.8B ChatShanghai AI Lab · 1.9BF165.6 GB59.6 tok/sRuns great
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 1.6BLiquid AI · 1.6BF164.3 GB71.3 tok/sRuns great
19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Llama 2 7B ChatMeta · 6.7BQ5_K_M7.9 GB58.8 tok/sRuns welltight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.TMax 27BAi2 · 27BQ5_K_M21.0 GB3.4 tok/sSlowheavy RAM offload
19Basic quality (D) · 19 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.Baichuan 2 7B ChatBaichuan · 7.5BQ4_K_M7.7 GB63.9 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 62/100 (quality, fit, speed and memory use) sets the ranking.Phi-4 Reasoning Plus (14B)Microsoft · 15BQ3_K_M9.9 GB18.7 tok/sRuns welloffloads to RAM
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Apriel 1.5 15B ThinkerServiceNow · 15BQ3_K_M9.9 GB18.4 tok/sRuns welloffloads to RAM
86Excellent quality (A+) · 86 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.Gemma 4 31BGoogle · 31BQ4_K_M21.7 GB3.4 tok/sSlowheavy RAM offload
16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.StableLM Zephyr 3BStability AI · 2.8BQ8_05.3 GB87.3 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Yi Coder 1.5B Chat01.AI · 1.5BF165.6 GB76.1 tok/sRuns great
18Basic quality (D) · 18 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.StarCoder 15BBigCode · 16BQ2_K7.5 GB49.8 tok/sRuns welltight fit
18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Granite 3.0 3B-A800M InstructIBM · 3.4B (0.8B active)Q8_04.8 GB141 tok/sRuns great
49Fair quality (C) · 49 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.ERNIE 4.5 21B-A3B ThinkingBaidu · 22B (3.0B active)Q2_K10.2 GB86.2 tok/sRuns welloffloads to RAM
49Fair quality (C) · 49 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.Maple Preview (20B-A1B)DeepGrove · 20B (1.5B active)Q2_K9.2 GB157 tok/sRuns welloffloads to RAM
62Good quality (B) · 62 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.Kimi Linear 48B-A3BMoonshot AI · 49B (3.0B active)Q3_K_M25.1 GB40.3 tok/sSlowheavy RAM offload
17Basic quality (D) · 17 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.DeepSeek LLM 7B ChatDeepSeek · 6.9BQ5_K_M7.9 GB57.4 tok/sRuns welltight fit
85Excellent quality (A+) · 85 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.Fara 1.5 27BMicrosoft · 27BQ5_K_M21.0 GB3.4 tok/sSlowheavy RAM offload
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-Omni 30B-A3B InstructAlibaba · 35B (3.3B active)Q4_K_M23.3 GB29.4 tok/sSlowheavy RAM offload
58Good quality (B) · 58 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.Phi-4 Reasoning (14B)Microsoft · 15BQ3_K_M9.9 GB18.7 tok/sRuns welloffloads to RAM
17Basic quality (D) · 17 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 2BFastino · 1.9BF164.9 GB59.9 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Trinity Mini (26B-A3B)Arcee AI · 26B (3.0B active)Q4_K_M17.1 GB37.1 tok/sSlowheavy RAM offload
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.LFM2 1.2BLiquid AI · 1.2BF163.4 GB96.3 tok/sRuns great
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_K8.0 GB117 tok/sRuns welltight fit
47Fair quality (C) · 47 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.Groot 19B A3B 261023GrootTeam · 19B (3.0B active)Q3_K_M10.7 GB68.0 tok/sRuns welloffloads to RAM
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Falcon 3 1B InstructTII · 1.7BF164.9 GB67.4 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 14BAlibaba · 15BQ2_K8.3 GB43.8 tok/sRuns welloffloads to RAM
58Good quality (B) · 58 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.Phi-4 Reasoning Vision 15BMicrosoft · 15BQ3_K_M10.1 GB17.3 tok/sRuns welloffloads to RAM
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 2BGoogle · 2.5BF166.2 GB44.9 tok/sRuns great
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-Math 1.5B InstructAlibaba · 1.5BF164.2 GB73.1 tok/sRuns great
13Basic quality (D) · 13 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.LLaVA 1.5 7BLLaVA · 7.1BQ3_K_M6.6 GB87.9 tok/sRuns great
13Basic quality (D) · 13 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.OLMo 7B InstructAi2 · 6.9BQ4_K_M6.3 GB69.7 tok/sRuns great
18Basic quality (D) · 18 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.StarCoder2 3BBigCode · 3.0BQ8_04.5 GB80.7 tok/sRuns great
83Great quality (A) · 83 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.UI-Mate 27BTencent · 27BQ5_K_M21.0 GB3.4 tok/sSlowheavy RAM offload
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.Hermes 4 14BNous Research · 15BQ2_K8.3 GB44.3 tok/sRuns welloffloads to RAM
22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.2 1B InstructMeta · 1.2BF163.7 GB90.8 tok/sRuns great
16Basic quality (D) · 16 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.Phi-2 2.7BMicrosoft · 2.8BQ8_04.6 GB87.9 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 1.3B InstructDeepSeek · 1.4BF165.3 GB83.4 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2B ITGoogle · 2.5BF166.2 GB44.9 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 1.3B V2LLM4Binary · 1.4BF165.3 GB83.4 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.AceReason Nemotron 14BNVIDIA · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
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.OpenReasoning Nemotron 14BNVIDIA · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
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.Qwen2.5 Coder 14B InstructAlibaba · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
11Basic quality (D) · 11 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.Vicuna 7B v1.5LMSYS · 6.7BQ3_K_M6.5 GB92.1 tok/sRuns great
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.Spark X2.6 1.7BSparkLLM · 1.7BF164.5 GB65.9 tok/sRuns great
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking.SmolLM 1.7B InstructHugging Face · 1.7BF164.8 GB65.9 tok/sRuns great
44Fair quality (C) · 44 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.ERNIE 4.5 21B-A3BBaidu · 22B (3.0B active)Q2_K10.2 GB85.7 tok/sRuns welloffloads to RAM
11Basic quality (D) · 11 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.InternLM 7BShanghai AI Lab · 7.3BQ4_K_M6.5 GB65.6 tok/sRuns great
55Good quality (B) · 55 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.Apriel Nemotron 15B ThinkerServiceNow · 15BQ3_K_M10.0 GB17.8 tok/sRuns welloffloads to RAM
26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Qwen3.5 0.8BAlibaba · 0.9BF162.8 GB129 tok/sRuns great
44Fair quality (C) · 44 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.DeepCoder 14B PreviewAgentica · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 1.5B InstructAlibaba · 1.5BF164.3 GB73.1 tok/sRuns great
43Fair quality (C) · 43 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.JanusCoder 14BShanghai AI Lab · 15BQ2_K8.3 GB44.3 tok/sRuns welloffloads to RAM
44Fair quality (C) · 44 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.Phi-4 (14B)Microsoft · 15BQ2_K8.6 GB36.7 tok/sRuns welloffloads to RAM
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 1B InstructAi2 · 1.5BF164.5 GB76.1 tok/sRuns great
43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 14B InstructAlibaba · 15BQ2_K8.5 GB38.1 tok/sRuns welloffloads to RAM
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 1.6B ChatStability AI · 1.6BF165.1 GB68.7 tok/sRuns great
10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking.StableLM 2 Zephyr 1.6BStability AI · 1.6BF165.1 GB68.7 tok/sRuns great
53Fair quality (C) · 53 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.InternVL3 14BShanghai AI Lab · 15BQ3_K_M10.0 GB17.6 tok/sRuns welloffloads to RAM
58Good quality (B) · 58 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.Axion 1.0 35BAxion · 35B (3.0B active)Q4_K_M22.6 GB33.0 tok/sSlowheavy RAM offload
43Fair quality (C) · 43 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.DeepSeek R1 Distill Qwen 14BDeepSeek · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
42Fair quality (C) · 42 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.Qwen2.5 14B Instruct 1MAlibaba · 15BQ2_K8.5 GB37.4 tok/sRuns welloffloads to RAM
77Great quality (A) · 77 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.EXAONE 4.5 33BLG AI Research · 34BQ4_K_M22.7 GB3.2 tok/sSlowheavy RAM offload
56Good quality (B) · 56 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.NorthCUA Minibeipo-ai · 35B (3.0B active)Q4_K_M22.6 GB33.0 tok/sSlowheavy RAM offload
20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 1BGoogle · 1.0BF163.1 GB113 tok/sRuns great
39Basic quality (D) · 39 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.LFM2 24B-A2BLiquid AI · 24B (2.3B active)Q2_K10.7 GB99.3 tok/sRuns welloffloads to RAM
5Basic quality (D) · 5 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.Falcon 7B InstructTII · 7.2BQ5_K_M6.1 GB54.9 tok/sRuns great
75Great quality (A) · 75 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.Devstral Small 2 (24B)Mistral AI · 24BQ6_K22.0 GB3.1 tok/sSlowheavy RAM offload
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 0.6BAlibaba · 0.8BF163.4 GB150 tok/sRuns great
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.2 30BIBM · 29BQ4_K_M21.0 GB3.6 tok/sSlowheavy RAM offload
72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Olmo 3.1 32B ThinkAi2 · 32BQ4_K_M21.4 GB3.5 tok/sSlowheavy RAM offload
18Basic quality (D) · 18 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.LFM2 700MLiquid AI · 0.7BF162.6 GB152 tok/sRuns great
71Great quality (A) · 71 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.Magistral Small 1.2 (24B)Mistral AI · 24BQ6_K22.0 GB3.1 tok/sSlowheavy RAM offload
46Fair quality (C) · 46 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.Reka Flash 3.1 (21B)Reka AI · 21BQ2_K10.5 GB15.5 tok/sRuns welloffloads to RAM
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.GLM-4 32B 0414Zhipu AI · 33BQ4_K_M21.4 GB3.4 tok/sSlowheavy RAM offload
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.GLM-Z1 32B (0414)Zhipu AI · 33BQ4_K_M21.4 GB3.4 tok/sSlowheavy RAM offload
69Good quality (B) · 69 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Gemma 3 27B ITGoogle · 27BQ5_K_M21.3 GB3.4 tok/sSlowheavy RAM offload
32Basic quality (D) · 32 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.Phi-3 Medium 128K InstructMicrosoft · 14BQ2_K8.3 GB46.0 tok/sRuns welloffloads to RAM
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 1.1 (24B)Mistral AI · 24BQ6_K21.7 GB3.2 tok/sSlowheavy RAM offload
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.Magistral Small 2507Mistral AI · 24BQ6_K21.7 GB3.2 tok/sSlowheavy RAM offload
68Good quality (B) · 68 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.Granite 4.1 30BIBM · 29BQ4_K_M20.8 GB3.7 tok/sSlowheavy RAM offload
68Good quality (B) · 68 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.EXAONE 4.0 32BLG AI Research · 32BQ4_K_M21.3 GB3.5 tok/sSlowheavy RAM offload
68Good quality (B) · 68 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.Olmo 3.1 32B InstructAi2 · 32BQ4_K_M21.4 GB3.5 tok/sSlowheavy RAM offload
67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.MedGemma 27B Text ITGoogle · 27BQ5_K_M21.0 GB3.4 tok/sSlowheavy RAM offload
15Basic quality (D) · 15 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.surya ocr 2.5Datalab · 0.7BF162.5 GB163 tok/sRuns great
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Seed-OSS 36B InstructByteDance · 36BQ3_K_M20.9 GB3.8 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Granite 4.0 H Small (32B-A9B)IBM · 32B (9.0B active)Q4_K_M20.8 GB12.3 tok/sSlowheavy RAM offload
67Good quality (B) · 67 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.Magistral Small 2506Mistral AI · 24BQ6_K21.7 GB3.2 tok/sSlowheavy RAM offload
66Good quality (B) · 66 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4.3 36BNous Research · 36BQ3_K_M20.9 GB3.8 tok/sSlowheavy RAM offload
67Good quality (B) · 67 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.Mistral Small 3.2 24BMistral AI · 24BQ6_K22.0 GB3.1 tok/sSlowheavy RAM offload
65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32BAlibaba · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Qwen3-VL 32B InstructAlibaba · 33BQ3_K_M19.5 GB4.2 tok/sSlowheavy RAM offload
65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking.Terminal RSI 27BTeriminal-RSI · 28BQ5_K_M21.3 GB3.3 tok/sSlowheavy RAM offload
63Good quality (B) · 63 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Hemmingway 1.5Hemmingway · 27BQ4_K_M17.9 GB4.5 tok/sSlowheavy RAM offload
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.OpenReasoning Nemotron 32BNVIDIA · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Skywork OR1 32BSkywork · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 32BAlibaba · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Devstral Small 2505Mistral AI · 24BQ6_K21.7 GB3.2 tok/sSlowheavy RAM offload
14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 0.5B InstructTII · 0.5BF162.2 GB217 tok/sRuns great
28Basic quality (D) · 28 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.StarCoder2 15B InstructBigCode · 16BQ2_K8.1 GB47.4 tok/sRuns welloffloads to RAM
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3.1 24BMistral AI · 24BQ6_K22.0 GB3.1 tok/sSlowheavy RAM offload
11Basic quality (D) · 11 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.GLiDE 0.8BFastino · 0.8BF162.6 GB150 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.SenseNova 6.8 Code2VideoSenseTime · 27BQ4_K_M18.2 GB4.4 tok/sSlowheavy RAM offload
63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.InternVL3.5 38BShanghai AI Lab · 38BQ3_K_M22.0 GB3.5 tok/sSlowheavy RAM offload
6Basic quality (D) · 6 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.TinyLlama 1.1B ChatTinyLlama · 1.1BF163.2 GB102 tok/sRuns great
62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.EXAONE Deep 32BLG AI Research · 32BQ3_K_M18.8 GB4.4 tok/sSlowheavy RAM offload
8Basic quality (D) · 8 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.Hunyuan 0.5B InstructTencent · 0.5BF162.9 GB209 tok/sRuns great
28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.CodeGemma 7BGoogle · 8.5BQ3_K_M8.9 GB34.7 tok/sRuns welloffloads to RAM
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 3 24B (2501)Mistral AI · 24BQ4_K_M16.7 GB5.2 tok/sSlowheavy RAM offload
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.LFM2.5 350MLiquid AI · 0.4BF161.8 GB322 tok/sRuns great
10Basic quality (D) · 10 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.SmolVLM 500M InstructHugging Face · 0.5BF162.4 GB221 tok/sRuns great
12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.LFM2-VL 450MLiquid AI · 0.5BF162.0 GB250 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek R1 Distill Qwen 32BDeepSeek · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Codestral 22BMistral AI · 22BQ4_K_M16.5 GB5.4 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Dolphin Mistral 24B Venice EditionCognitive Computations · 24BQ4_K_M17.0 GB5.0 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Voxtral Small 24BMistral AI · 24BQ4_K_M17.1 GB4.9 tok/sSlowheavy RAM offload
47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Phi-3.5 MoE (42B-A6.6B)Microsoft · 42B (6.6B active)Q3_K_M22.6 GB19.7 tok/sSlowheavy RAM offload
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 350MLiquid AI · 0.4BF161.8 GB322 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Falcon-H1 34B InstructTII · 34BQ4_K_M22.7 GB3.2 tok/sSlowheavy RAM offload
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.Qwen2.5 0.5B InstructAlibaba · 0.5BF162.1 GB230 tok/sRuns great
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Baichuan M2 32BBaichuan · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.OpenHands LM 32BAll Hands AI · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 32B InstructAlibaba · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
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.Granite 4.0 H 350MIBM · 0.3BF161.7 GB331 tok/sRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Gemma 2 27B ITGoogle · 27BQ5_K_M22.1 GB3.2 tok/sSlowheavy RAM offload
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Solar Pro Preview 22BUpstage · 22BQ4_K_M15.8 GB5.7 tok/sSlowheavy RAM offload
22Basic quality (D) · 22 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.StarCoder2 15B (base)BigCode · 16BQ2_K8.1 GB47.4 tok/sRuns welloffloads to RAM
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.Dolphin 3.0 R1 Mistral 24BCognitive Computations · 24BQ4_K_M16.7 GB5.2 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.InternVL3 38BShanghai AI Lab · 38BQ3_K_M22.0 GB3.5 tok/sSlowheavy RAM offload
58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Command R (08-2024) 32BCohere · 32BQ4_K_M22.0 GB3.3 tok/sSlowheavy RAM offload
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek MoE 16B ChatDeepSeek · 16B (2.8B active)Q3_K_M10.0 GB76.2 tok/sRuns welloffloads to RAM
8Basic quality (D) · 8 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 Coder 0.5B InstructAlibaba · 0.5BF162.1 GB230 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5-VL 32B InstructAlibaba · 33BQ3_K_M19.5 GB4.2 tok/sSlowheavy RAM offload
23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Gemma 1.1 7B ITGoogle · 8.5BQ3_K_M8.9 GB34.7 tok/sRuns welloffloads to RAM
8Basic quality (D) · 8 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.SmolLM2 360M InstructHugging Face · 0.4BF162.1 GB313 tok/sRuns great
55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.LLM4Decompile 22B V2LLM4Binary · 22BQ4_K_M16.5 GB5.4 tok/sSlowheavy RAM offload
56Good quality (B) · 56 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 Coder 32B InstructAlibaba · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 MoE A2.7B ChatAlibaba · 14B (2.7B active)Q3_K_M9.6 GB80.0 tok/sRuns welloffloads to RAM
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 32B InstructAi2 · 32BQ4_K_M21.7 GB3.4 tok/sSlowheavy RAM offload
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Aya Expanse 32BCohere · 32BQ4_K_M22.0 GB3.3 tok/sSlowheavy RAM offload
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 · 0.2BF161.5 GB490 tok/sRuns great
57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Aya Vision 32BCohere · 33BQ4_K_M22.6 GB3.2 tok/sSlowheavy RAM offload
55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.QwQ 32B PreviewAlibaba · 33BQ3_K_M19.2 GB4.3 tok/sSlowheavy RAM offload
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Gemma 7B ITGoogle · 8.5BQ3_K_M8.9 GB34.7 tok/sRuns welloffloads to RAM
6Basic quality (D) · 6 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 0.5B InstructAlibaba · 0.5BF162.1 GB230 tok/sRuns great
21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 7B ChatAlibaba · 7.7BQ3_K_M9.1 GB33.7 tok/sRuns welloffloads to RAM
6Basic quality (D) · 6 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.ERNIE 4.5 0.3BBaidu · 0.4BF161.9 GB313 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 · 0.3BF161.7 GB433 tok/sRuns great
51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Mistral Small 22B (2409)Mistral AI · 22BQ4_K_M16.5 GB5.4 tok/sSlowheavy RAM offload
25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 20B InstructIBM · 20BQ2_K9.2 GB22.4 tok/sRuns welloffloads to RAM
5Basic quality (D) · 5 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.SmolLM 360M InstructHugging Face · 0.4BF161.8 GB313 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.Gemma 3 270MGoogle · 0.3BF161.6 GB417 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.InternLM2.5 20B ChatShanghai AI Lab · 20BQ4_K_M14.7 GB6.5 tok/sSlowheavy RAM offload
43Fair quality (C) · 43 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking.Nous Hermes 2 Mixtral 8x7B DPONous Research · 47B (12.9B active)Q3_K_M25.0 GB10.1 tok/sSlowheavy RAM offload
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 · 0.1BF161.4 GB866 tok/sRuns great
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Jamba 1.5 MiniAI21 Labs · 52B (12.0B active)Q3_K_M26.4 GB11.0 tok/sSlowheavy RAM offload
42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.Mixtral 8x7B InstructMistral AI · 47B (12.9B active)Q3_K_M25.0 GB10.1 tok/sSlowheavy RAM offload
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking.OLMo 2 13B InstructAi2 · 14BQ4_K_M12.7 GB9.3 tok/sSlowheavy RAM offload
3Basic quality (D) · 3 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.Falcon-H1 Tiny 90M InstructTII · 0.1BF161.3 GB1,252 tok/sRuns great
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 · 0.1BF161.3 GB866 tok/sRuns great
47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking.Yi 1.5 34B Chat01.AI · 34BQ4_K_M23.0 GB3.1 tok/sSlowheavy RAM offload
39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Chat 20BShanghai AI Lab · 20BQ4_K_M14.7 GB6.5 tok/sSlowheavy RAM offload
35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.Qwen2 57B-A14B InstructAlibaba · 57B (14.0B active)Q2_K24.4 GB12.1 tok/sSlowheavy RAM offload
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.InternLM2 Math Plus 20BShanghai AI Lab · 20BQ4_K_M14.7 GB6.5 tok/sSlowheavy RAM offload
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.6 34BLLaVA · 35BQ4_K_M23.2 GB3.1 tok/sSlowheavy RAM offload
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.Qwen1.5 32B ChatAlibaba · 33BQ3_K_M19.1 GB4.4 tok/sSlowheavy RAM offload
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder 33B InstructDeepSeek · 33BQ3_K_M19.4 GB4.2 tok/sSlowheavy RAM offload
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.Granite Code 34B InstructIBM · 34BQ4_K_M21.9 GB3.3 tok/sSlowheavy RAM offload
38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 40/100 (quality, fit, speed and memory use) sets the ranking.Yi 34B Chat01.AI · 34BQ4_K_M23.0 GB3.1 tok/sSlowheavy RAM offload
31Basic quality (D) · 31 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking.CogVLM2 Llama 3 Chat 19BZhipu AI · 20BQ3_K_M14.8 GB7.1 tok/sSlowheavy RAM offload
19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking.Orca 2 13BMicrosoft · 13BQ2_K9.6 GB24.6 tok/sSlowheavy RAM offload
36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 39/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 34B InstructMeta · 34BQ4_K_M23.2 GB3.1 tok/sSlowheavy RAM offload
18Basic quality (D) · 18 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.Llama 2 13B ChatMeta · 13BQ2_K9.6 GB24.6 tok/sSlowheavy RAM offload
18Basic quality (D) · 18 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.Baichuan 2 13B ChatBaichuan · 14BQ2_K9.9 GB21.2 tok/sSlowheavy RAM offload
15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 37/100 (quality, fit, speed and memory use) sets the ranking.WizardLM 13B v1.2WizardLM · 13BQ2_K9.6 GB24.6 tok/sSlowheavy RAM offload
15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 37/100 (quality, fit, speed and memory use) sets the ranking.LLaVA 1.5 13BLLaVA · 13BQ2_K9.7 GB23.2 tok/sSlowheavy RAM offload
14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 37/100 (quality, fit, speed and memory use) sets the ranking.Vicuna 13B v1.5LMSYS · 13BQ2_K9.6 GB24.6 tok/sSlowheavy RAM offload
13Basic quality (D) · 13 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 29/100 (quality, fit, speed and memory use) sets the ranking.Falcon 40B InstructTII · 42BQ3_K_M21.7 GB3.5 tok/sSlowheavy RAM offload
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)MXFP467.9 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_K1,113 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_K306 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_K303 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_K980 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_K1,113 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_K411 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_K243 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_K306 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_K73.2 GB—Won't run
67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.GLM-5.2 (753B-A40B)Zhipu AI · 753B (40.0B active)Q2_K303 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_K330 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_K412 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_K303 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_K160 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_K641 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_K303 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_K123 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_K412 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_K412 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_K123 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_K50.8 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.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_K147 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_K382 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_K94.6 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_K82.0 GB—Won't run
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking.Nemotron 3 Ultra 550B-A55BNVIDIA · 561B (55.0B active)Q2_K225 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_K275 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_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.Ornith 1.5 122B-A10BDeepReinforce · 125B (10.0B active)Q2_K51.2 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_K411 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_K94.6 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.Nemotron 3.5 Bolt 74B-A9BNVIDIA · 75B (9.0B active)Q2_K31.0 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_K270 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.Qwen3.5 122B-A10BAlibaba · 125B (10.0B active)Q2_K51.2 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_K81.2 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_K275 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_K275 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_K412 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_K32.4 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_K94.6 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.Qwen3 235B-A22B Thinking 2507Alibaba · 235B (22.0B active)Q2_K96.6 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.Qwen3 Coder 480B-A35BAlibaba · 480B (35.0B active)Q2_K195 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_K125 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.Qwen3 235B-A22B Instruct 2507Alibaba · 235B (22.0B active)Q2_K96.6 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.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.Kimi K2 Instruct (July 2025)Moonshot AI · 1,026B (32.0B active)Q2_K412 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_K94.6 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_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.Command A+ (218B-A25B)Cohere · 219B (25.0B active)Q2_K88.8 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.K-EXAONE 236B-A23BLG AI Research · 237B (23.0B active)Q2_K96.3 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.LongCat Flash Chat (560B)Meituan · 562B (27.0B active)Q2_K226 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_K50.5 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_K96.6 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_K54.0 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_K98.9 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_K49.6 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.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_K33.1 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.Qwen3-Next 80B-A3B ThinkingAlibaba · 81B (3.0B active)Q2_K33.7 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_K96.6 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_K33.7 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_K275 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_K45.6 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_K46.2 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_K147 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_K52.4 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_K48.9 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_K55.0 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Trinity Large Thinking (400B-A13B)Arcee AI · 399B (13.0B active)Q2_K161 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_K46.2 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.ERNIE 4.5 300B-A47BBaidu · 300B (47.0B active)Q2_K123 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_K45.6 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.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_K32.8 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Ling 2.6 Flash (104B-A7.4B)Ant Group (inclusionAI) · 107B (7.4B active)Q2_K44.0 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.3 Nemotron Super 49B v1.5NVIDIA · 50BQ2_K23.6 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.Mistral Large 2.1 (2411)Mistral AI · 123BQ2_K53.0 GB—Won't run
56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking.Solar Open 100BUpstage · 103B (12.0B active)Q2_K43.7 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.GLM-4.5 Air (106B-A12B)Zhipu AI · 110B (12.0B active)Q2_K46.7 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.Mistral Large 2 (123B)Mistral AI · 123BQ2_K53.2 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.NorthCUA Probeipo-ai · 397B (17.0B active)Q2_K160 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_K53.6 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_K42.7 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_K66.4 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.Ling Flash 2.0 (100B-A6B)Ant Group (inclusionAI) · 103B (6.1B active)Q2_K42.7 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.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_K270 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_K43.7 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_K95.9 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Hermes 4 70BNous Research · 71BQ2_K31.9 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan A13B (80B-A13B)Tencent · 80B (13.0B active)Q2_K34.2 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_K35.0 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Leanstral 119B-A6BMistral AI · 119B (6.5B active)Q2_K48.9 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.3 70B InstructMeta · 71BQ2_K31.9 GB—Won't run
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.Qwen2.5 72B InstructAlibaba · 73BQ2_K32.8 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-VL 72B InstructAlibaba · 73BQ2_K33.0 GB—Won't run
50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek Coder V2 Instruct (0614)DeepSeek · 236B (21.0B active)Q2_K95.9 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_K31.9 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_K95.9 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_K163 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_K46.1 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.Tülu 3 70BAi2 · 71BQ2_K31.9 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_K44.7 GB—Won't run
49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.DeepSeek V2.5DeepSeek · 236B (21.0B active)Q2_K95.9 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_K48.5 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.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_K31.9 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_K31.9 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_K52.1 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_K33.0 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.Apertus v1.5 70BSwiss AI · 72BQ2_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 3.1 Nemotron 70B InstructNVIDIA · 71BQ2_K31.9 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_K39.8 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_K44.7 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_K32.8 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.Qwen2-VL 72B InstructAlibaba · 73BQ2_K33.0 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_K95.9 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_K31.9 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_K31.9 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_K31.4 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_K59.1 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_K25.7 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_K48.2 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_K25.7 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.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.Snowflake Arctic InstructSnowflake · 479B (17.0B active)Q2_K193 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_K29.9 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_K29.6 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_K29.9 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_K73.1 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.Qwen1.5 14B ChatAlibaba · 14BQ2_K13.4 GB—Won't run
21Basic quality (D) · 21 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 2/100 (quality, fit, speed and memory use) sets the ranking.Code Llama 13B InstructMeta · 13BQ2_K12.9 GB—Won't run

Image models on the Intel Arc A580

Quality Model Quant Memory Speed Runs
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 4BBlack Forest Labs · 3.9BQ8 GGUF6.4 GB5.4 sRuns greatencoder in RAM
78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Z-Image TurboAlibaba (Tongyi) · 6.2BQ4 GGUF6.1 GB14 sRuns wellencoder in RAM
84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.FLUX 3 Image KleinBlack Forest Labs · 5.6BQ4 GGUF5.7 GB32 sRuns wellencoder in RAM
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.DreamShaper XL v2 TurboLykon · 2.6BFP85.6 GB5.2 sRuns great
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-Image TurboBaidu · 8.0BQ4 GGUF7.4 GB18 sRuns welltight fit · encoder in RAM
82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.FLUX.2 [klein] 9BBlack Forest Labs · 9.1BFP85.6 GB9.4 sRuns greatCPU offload
52Fair quality (C) · 52 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.SDXL-Lightning (4-step)ByteDance · 2.6BFP85.6 GB2.8 sRuns great
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Juggernaut XL v9RunDiffusion · 2.6BFP85.6 GB18 sRuns well
60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.RealVisXL V5.0SG161222 · 2.6BFP85.6 GB18 sRuns well
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Animagine XL 4.0Cagliostro Lab · 2.6BFP85.6 GB17 sRuns well
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.Illustrious XL v0.1OnomaAI · 2.6BFP85.6 GB17 sRuns well
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Pony Diffusion V6 XLPurpleSmartAI · 2.6BFP85.6 GB15 sRuns well
54Fair quality (C) · 54 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.Animagine XL 3.1Cagliostro Lab · 2.6BFP85.6 GB17 sRuns well
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Krea 2 TurboKrea · 12.8BFP87.1 GB22 sRuns welltight fit · CPU offload
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion XL 1.0Stability AI · 2.6BFP85.6 GB18 sRuns well
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.MOSS-Image SFTOpenMOSS · 5.1BFP87.4 GB59 sSlowtight fit · encoder in RAM
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.Playground v2.5Playground AI · 2.6BFP85.6 GB30 sRuns well
60Good quality (B) · 60 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.Lumina-Image 2.0Shanghai AI Lab · 2.6BFP87.5 GB28 sRuns welltight fit
76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.Z-ImageAlibaba (Tongyi) · 6.2BQ4 GGUF6.1 GB1.6 minSlowencoder in RAM
81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.ERNIE-ImageBaidu · 8.0BQ4 GGUF7.4 GB2.1 minSlowtight fit · encoder in RAM
57Good quality (B) · 57 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 Large TurboStability AI · 8.1BQ4 GGUF7.5 GB9.0 sRuns welltight fit · encoder in RAM
58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.KolorsKuaishou · 2.6BFP84.8 GB17 sRuns wellencoder in RAM
68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 [schnell]Black Forest Labs · 11.9BFP86.8 GB10 sRuns welltight fit · CPU offload
72Great quality (A) · 72 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.Chroma1-HDLodestone Rock · 8.9BNF47.7 GB1.7 minSlowtight fit · encoder in RAM
39Basic quality (D) · 39 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.SDXL TurboStability AI · 2.6BFP84.2 GB0.6 sRuns great
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) · 4.0BFP86.6 GB68 sSlowencoder in RAM
85Excellent quality (A+) · 85 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.Ideogram 4Ideogram · 18.6BNF46.1 GB2.7 minVery slowCPU offload
56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3.5 MediumStability AI · 2.5BFP84.8 GB25 sRuns wellencoder in RAM
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 3 MediumStability AI · 2.0BFP84.3 GB13 sRuns greatencoder in RAM
53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.AuraFlow v0.3fal · 6.9BQ4 GGUF7.7 GB75 sSlowtight fit
52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.Hunyuan-DiT v1.2Tencent · 1.5BFP165.2 GB28 sRuns wellencoder in RAM
80Great quality (A) · 80 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.FLUX.1 Krea [dev]Black Forest Labs · 11.9BFP86.8 GB63 sSlowtight fit · CPU offload
50Fair quality (C) · 50 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.PixArt-Σ XL 1024PixArt · 0.6BFP163.3 GB7.0 sRuns greatencoder in RAM
42Fair quality (C) · 42 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.Realistic Vision V5.1SG161222 · 0.9BFP162.8 GB5.4 sRuns great
61Good quality (B) · 61 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.Stable Diffusion 3.5 LargeStability AI · 8.1BQ4 GGUF7.5 GB62 sSlowtight fit · encoder in RAM
78Great quality (A) · 78 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.FLUX.1 [dev]Black Forest Labs · 11.9BFP86.8 GB63 sSlowtight fit · CPU offload
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 · 5.2BFP87.4 GB21 sRuns welltight fit · encoder in RAM
40Fair quality (C) · 40 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.DreamShaper 8Lykon · 0.9BFP162.8 GB5.4 sRuns great
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Kontext [dev]Black Forest Labs · 11.9BFP87.5 GB1.9 minSlowtight fit · CPU offload
74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 DevHiDream.ai · 17.1BNF46.2 GB1.8 minSlowCPU offload
78Great quality (A) · 78 of 100: how capable the model is at NF4, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FullHiDream.ai · 17.1BNF46.2 GB4.8 minVery slowCPU offload
70Great quality (A) · 70 of 100: how capable the model is at NF4, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.HiDream-I1 FastHiDream.ai · 17.1BNF46.2 GB64 sSlowCPU offload
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking.FLUX.1 Fill [dev]Black Forest Labs · 11.9BFP86.8 GB65 sSlowtight fit · CPU offload
35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.Stable Diffusion 1.5Stability AI / Runway · 0.9BFP162.8 GB5.4 sRuns great
70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.CogView4 6BZhipu AI · 6.4BFP166.7 GB1.7 minSlowCPU offload
72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.Iris-3BSperidlabs · 3.0BFP164.5 GB1.5 minSlowCPU offload
28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.SD TurboStability AI · 0.9BFP163.3 GB0.4 sRuns great
30Basic quality (D) · 30 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.LCM DreamShaper v7Tsinghua (LCM) · 0.9BFP162.8 GB1.1 sRuns great
48Fair quality (C) · 48 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.Kandinsky 3Sber AI · 3.0BFP164.2 GB52 sSlowCPU offload
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.Fibo 2.0 DevBria AI · 8.1BFP168.1 GB—Won't run
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
85Excellent quality (A+) · 85 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.FLUX.2 [dev]Black Forest Labs · 32.2BQ4 GGUF10.1 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
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.Qwen-Image 2512Alibaba · 20.4BQ4 GGUF10.4 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
80Great quality (A) · 80 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.FireRed-Image-Edit 1.1rednote (FireRed Team) · 20.4BQ4 GGUF7.8 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.Qwen-Image-Edit 2511Alibaba · 20.4BQ4 GGUF7.8 GB—Won't run

Video models on the Intel Arc A580

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 72/100 (quality, fit, speed and memory use) sets the ranking.LTX-Video 2BLightricks · 1.9BFP86.1 GB1.8 minRuns greatencoder in RAM
35Basic quality (D) · 35 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.AnimateDiff v3 (SD 1.5)Shanghai AI Lab · 1.3BFP164.7 GB89 sRuns great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.CogVideoX 2BZhipu AI · 1.7BFP86.2 GB4.2 minRuns wellencoder in RAM
53Fair quality (C) · 53 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.Wan 2.1 T2V 1.3BAlibaba · 1.3BFP87.1 GB16.9 minSlowtight fit · encoder in RAM
53Fair quality (C) · 53 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.CogVideoX 5BZhipu AI · 5.0BFP85.9 GB15.7 minSlowCPU offload
53Fair quality (C) · 53 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.CogVideoX 5B I2VZhipu AI · 5.6BFP86.1 GB15.7 minSlowCPU offload
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 VACE 1.3BAlibaba · 2.2BFP86.3 GB22.6 minSlowCPU offload
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.Cosmos3-Super Image2Video (64B)NVIDIA · 64.0BFP1653.7 GB—Won't run
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
83Great quality (A) · 83 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.Bernini-R A14B (video generation + editing)ByteDance · 14.3BFP810.7 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.HY-OmniWeaving (8.3B, unified video)Tencent · 8.3BFP87.8 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.FramePack I2V (HunyuanVideo 13B)lllyasviel · 12.9BFP810.8 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 Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.2 S2V 14B (speech to video)Alibaba · 16.3BQ4 GGUF9.0 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 Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking.Wan 2.1 I2V 14B 480PAlibaba · 14.0BQ4 GGUF8.5 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
68Good quality (B) · 68 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.Kandinsky 6.0 Video Lite (3B, video + audio)Sber AI · 3.2BFP168.9 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
50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking.SkyReels V2 Diffusion Forcing 1.3BSkywork · 1.4BFP89.8 GB—Won't run

Decision models on the Intel Arc A580

Quality Model Quant Memory Speed Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v3.5Jina AI · 600MF162.4 GB32 msRuns great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v3Jina AI · 600MF162.4 GB32 msRuns great
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.Intern-Decision 4BShanghai AI Lab · 4.5BQ8_05.9 GB108 msRuns great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 4BAlibaba · 4.0BQ8_05.6 GB173 msRuns well
82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.d1 3BLiquid AI · 3.1BQ8_04.3 GB76 msRuns great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.mxbai-rerank-large v2Mixedbread · 1.5BF164.1 GB76 msRuns great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.zerank-2ZeroEntropy · 4.0BQ8_05.6 GB173 msRuns well
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.FRIDA-DecisionsSber AI · 820MF162.4 GB23 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.GLiNER2.5 DecideFastino · 490MF161.7 GB16 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.LemonDecider 4BAnt Group (inclusionAI) · 4.5BQ8_06.5 GB97 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 0.6BAlibaba · 600MF162.4 GB32 msRuns great
80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.zerank-1 smallZeroEntropy · 1.7BF164.7 GB84 msRuns great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.Shieldstral 1.0 3BMistral AI · 3.9BQ8_05.3 GB165 msRuns well
78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.BGE Reranker v2 GemmaBAAI · 2.5BQ8_03.7 GB109 msRuns great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 86MMeta · 280MF161.2 GB17 msRuns great
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.mxbai-rerank-base v2Mixedbread · 490MF162.0 GB27 msRuns great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.GLiClass ModernBERT Large v3Knowledgator · 400MF161.5 GB13 msRuns great
78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.OpenAI Privacy FilterOpenAI · 1.4B (50M active)F163.8 GB5.2 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.BGE Reranker v2 M3BAAI · 570MF161.9 GB31 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.DeBERTa v3 Large Zero-shot v2.0Moritz Laurer · 440MF161.6 GB14 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.DuoGuard 0.5BDuoGuard · 490MF161.7 GB27 msRuns great
72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.Skywork Reward V2 Qwen3 0.6BSkywork · 600MF162.0 GB61 msRuns great
85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Qwen3 Reranker 8BAlibaba · 8.2BQ4_K_M6.3 GB331 msRuns well
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.GTE Reranker ModernBERT BaseAlibaba · 150MF160.9 GB11 msRuns great
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.Jina Reranker v2 Base MultilingualJina AI · 280MF161.2 GB17 msRuns great
70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.ModernBERT Large Zero-shot v2.0Moritz Laurer · 400MF161.5 GB13 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.GLiGuard 300MFastino · 210MF161.1 GB14 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Granite Embedding Reranker English R2IBM · 150MF160.9 GB11 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.LayaConvai Innovations · 420MF161.5 GB14 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Llama Prompt Guard 2 22MMeta · 71MF160.8 GB7.4 msRuns great
74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.Qwen3Guard Gen 0.6BAlibaba · 750MF162.7 GB72 msRuns great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.GLiClass Base v3Knowledgator · 190MF161.0 GB8.5 msRuns great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.ProtectAI DeBERTa v3 Prompt Injection v2Protect AI · 180MF161.0 GB13 msRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.Qwen3Guard Gen 4BAlibaba · 4.4BQ6_K4.9 GB250 msRuns well
64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.DeBERTa v3 Base Zero-shot v2.0Moritz Laurer · 180MF161.0 GB8.3 msRuns great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.GLiNER2 Base v1Fastino · 210MF161.1 GB9.0 msRuns great
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.HHEM 2.1 OpenVectara · 110MF160.8 GB14 msRuns great
66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.LettuceDetect LargeKR Labs · 400MF161.5 GB42 msRuns great
60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.Laya MultilingualConvai Innovations · 320MF161.3 GB12 msRuns great
81Great quality (A) · 81 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.Qwen3Guard Gen 8BAlibaba · 8.2BQ4_K_M6.3 GB416 msSlow
62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.GLiNER Multi v2.1Urchade Zaratiana · 290MF161.3 GB11 msRuns great
83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Llama 3.1 Nemotron Safety Guard 8B v3NVIDIA · 8.0BQ6_K7.9 GB453 msSlowtight fit
56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.BART Large MNLIMeta · 410MF161.5 GB14 msRuns great
58Good quality (B) · 58 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.ShieldGemma 2BGoogle · 2.6BQ8_04.0 GB113 msRuns great
79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.Granite Guardian 4.1 8BIBM · 8.4BQ4_K_M6.4 GB426 msSlow
75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.NuExtract 2.0 4BNuMind · 3.8BQ6_K4.2 GB345 msRuns well
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.NuExtract 2.0 2BNuMind · 2.2BQ4_K_M2.4 GB156 msRuns well
77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.WildGuard 7BAi2 · 7.3BQ5_K_M6.4 GB388 msRuns well
76Great quality (A) · 76 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 Guardian 3.3 8BIBM · 8.2BQ4_K_M6.3 GB415 msSlow
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 GB5.1 msRuns great
56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.Llama Guard 3 1BMeta · 1.5BQ8_02.7 GB98 msRuns great
60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 9BGoogle · 9.2BQ4_K_M7.3 GB373 msRuns welltight fit
64Good quality (B) · 64 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.Llama Guard 3 8BMeta · 8.0BQ4_K_M6.2 GB408 msSlow
77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.Nemotron Content Safety Reasoning 4BNVIDIA · 4.3BQ6_K4.8 GB2.2 sVery slow
75Great quality (A) · 75 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.DynaGuard 8BUniversity of Maryland · 8.2BQ4_K_M6.3 GB3.0 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_K7.9 GB4.2 sVery slowtight fit
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.DynaGuard 1.7BUniversity of Maryland · 2.0BQ6_K2.9 GB1.1 sSlow
75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.CompassJudger-2 7BOpenCompass · 7.6BQ5_K_M6.5 GB3.5 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.GLIDERPatronus AI · 3.8BQ6_K4.9 GB2.0 sVery slow
65Good quality (B) · 65 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.Prometheus 2 7BPrometheus Eval · 7.2BQ5_K_M6.4 GB3.3 sVery slow
63Good quality (B) · 63 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.Flow Judge v0.1Flow AI · 3.8BQ6_K4.9 GB2.0 sVery slow
62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking.Llama Guard 4 12BMeta · 12BQ4_K_M8.7 GB714 msSlowoffloads to RAM
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.ShieldGemma 27BGoogle · 27BQ6_K24.1 GB2.4 sVery slowheavy RAM offload
83Great quality (A) · 83 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.CompassJudger-2 32BOpenCompass · 33BQ5_K_M24.8 GB60.9 sVery slowheavy RAM offload
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking.gpt-oss-safeguard 20BOpenAI · 22B (3.6B active)MXFP413.3 GB4.2 sVery slowheavy RAM offload
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.Skywork Reward V2 Llama 3.1 8BSkywork · 7.5BQ8_010.4 GB—Won't run
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
84Great quality (A) · 84 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.Skywork Reward V2 Qwen3 8BSkywork · 7.6BQ8_010.5 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)MXFP467.7 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_M29.8 GB—Won't run

Upgrade picks

GPUs that would run more LLMs without offloading, at launch prices. Right now 337 of 619 LLMs run well on your Intel Arc A580.

ASRock Intel Arc B570 Challenger 10GB OC Cheapest upgrade Intel Arc B570 10.0 GB · $219 launch price +47 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 +119 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 +209 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?