Raspberry Pi 4 (2 GB) spec sheet
What the Raspberry Pi 4 (2 GB) can run
We check your GPU or device against every model. Browsers can’t see how much memory you have, so confirm your exact model below.
- Unified memory
- 2.0 GB
- Usable for models
- 1.2 GB
- Memory bandwidth
- 13 GB/s
- FP16 compute
- 0.1 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on the Raspberry Pi 4 (2 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 8Basic quality (D) · 8 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 230M | Q3_K_M | 0.9 GB | 36.8 tok/s | Runs great |
| 9Basic quality (D) · 9 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. | LFM2.5 350M | Q2_K | 0.9 GB | 30.7 tok/s | Runs great |
| 8Basic quality (D) · 8 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. | Granite 4.0 H 350M | Q2_K | 0.9 GB | 31.6 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 350M | Q2_K | 0.9 GB | 30.7 tok/s | Runs great |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 256M Instruct | Q2_K | 1.0 GB | 41.4 tok/s | Runs great |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 270M | Q2_K | 0.8 GB | 39.8 tok/s | Runs great |
| 3Basic quality (D) · 3 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 135M Instruct | Q5_K_M | 1.0 GB | 41.6 tok/s | Runs great |
| 2Basic quality (D) · 2 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 Tiny 90M Instruct | Q6_K | 0.9 GB | 50.5 tok/s | Runs great |
| 1Basic quality (D) · 1 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 135M Instruct | Q5_K_M | 0.8 GB | 41.6 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q2_K | 1.1 GB | 12.4 tok/s | Runs welltight fit |
| 8Basic quality (D) · 8 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. | LFM2-VL 450M | Q2_K | 1.0 GB | 23.9 tok/s | Runs well |
| 4Basic quality (D) · 4 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. | ERNIE 4.5 0.3B | Q2_K | 1.0 GB | 29.9 tok/s | Runs well |
| 3Basic quality (D) · 3 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. | SmolLM 360M Instruct | Q2_K | 0.9 GB | 29.9 tok/s | Runs well |
| 5Basic quality (D) · 5 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. | SmolLM2 360M Instruct | Q2_K | 1.2 GB | 29.9 tok/s | Runs welltight fit |
| 7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 0.5B Instruct | Q2_K | 1.0 GB | 21.9 tok/s | Runs well |
| 9Basic quality (D) · 9 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. | Falcon-H1 0.5B Instruct | Q2_K | 1.1 GB | 20.7 tok/s | Runs welltight fit |
| 15Basic quality (D) · 15 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. | LFM2 700M | Q3_K_M | 1.2 GB | 11.4 tok/s | Runs welltight fit |
| 5Basic quality (D) · 5 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 0.5B Instruct | Q2_K | 1.0 GB | 21.9 tok/s | Runs well |
| 10Basic quality (D) · 10 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | surya ocr 2.5 | Q2_K | 1.1 GB | 15.6 tok/s | Runs welltight fit |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 1B | Q2_K | 1.1 GB | 10.8 tok/s | Runs welltight fit |
| 4Basic quality (D) · 4 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. | Qwen2 0.5B Instruct | Q2_K | 1.0 GB | 21.9 tok/s | Runs well |
| 7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 0.8B | Q2_K | 1.1 GB | 14.3 tok/s | Runs welltight fit |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | TinyLlama 1.1B Chat | Q2_K | 1.2 GB | 9.8 tok/s | Slowtight fit |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | Q3_K_M | 1.3 GB | 7.5 tok/s | Slowover memory limit |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q2_K | 1.3 GB | 7.0 tok/s | Slowover memory limit |
| 39Basic quality (D) · 39 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. | LFM3 1.7B | Q2_K | 1.5 GB | 5.3 tok/s | Slowfar over memory limit |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 41/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q2_K | 1.3 GB | 7.8 tok/s | Slowover memory limit |
| 18Basic quality (D) · 18 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. | LFM2 1.2B | Q2_K | 1.3 GB | 7.8 tok/s | Slowover memory limit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 38/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | Q3_K_M | 1.4 GB | 6.7 tok/s | Slowfar over memory limit |
| 7Basic quality (D) · 7 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. | SmolVLM 500M Instruct | Q2_K | 1.2 GB | 17.9 tok/s | Runs wellover memory limit |
| 28Basic quality (D) · 28 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. | MiniCPM-V 4.7 1B | Q2_K | 1.4 GB | 5.9 tok/s | Slowfar over memory limit |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 34/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 1B | Q3_K_M | 1.5 GB | 4.9 tok/s | Slowfar over memory limit |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 32/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 1B Instruct | Q2_K | 1.5 GB | 7.4 tok/s | Slowfar over memory limit |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 32/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 1.6B | Q2_K | 1.4 GB | 5.8 tok/s | Slowfar over memory limit |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 31/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 1.5B Instruct | Q2_K | 1.4 GB | 5.9 tok/s | Slowfar over memory limit |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 29/100 (quality, fit, speed and memory use) sets the ranking. | Spark X2.6 1.7B | Q2_K | 1.5 GB | 5.3 tok/s | Slowfar over memory limit |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 67.6 GB | — | Won't run |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 12.8 GB | — | Won't run |
| 69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K3.1 Pro (2.8T) | Q2_K | 1,113 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) | Q2_K | 306 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) | Q2_K | 303 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) | Q2_K | 980 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) | Q2_K | 1,113 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) | Q2_K | 411 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) | Q2_K | 230 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) | Q2_K | 173 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) | Q2_K | 243 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) | Q2_K | 129 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) | Q2_K | 125 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) | Q2_K | 306 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) | Q2_K | 423 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) | Q2_K | 72.9 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) | Q2_K | 303 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) | Q2_K | 313 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) | Q2_K | 330 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) | Q2_K | 661 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) | Q2_K | 412 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.3 33B | Q2_K | 15.7 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) | Q2_K | 230 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) | Q2_K | 411 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. | Qwen3.8 27B | Q2_K | 12.3 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) | Q2_K | 162 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) | Q2_K | 303 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) | Q2_K | 160 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) | Q2_K | 641 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) | Q2_K | 124 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-A17B | Q2_K | 162 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) | Q2_K | 173 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) | Q2_K | 303 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) | Q2_K | 154 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) | Q2_K | 123 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) | Q2_K | 202 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) | Q2_K | 412 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) | Q2_K | 412 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) | Q2_K | 123 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) | Q2_K | 125 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-A17B | Q2_K | 162 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 27B | Q2_K | 12.3 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-A12B | Q2_K | 50.5 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.2 (671B) | Q2_K | 275 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) | Q2_K | 107 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) | Q2_K | 147 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) | Q2_K | 382 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) | Q2_K | 94.3 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q2_K | 15.2 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.7 Flash (198B-A11B) | Q2_K | 81.7 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q2_K | 14.9 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Ultra 550B-A55B | Q2_K | 225 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) | Q2_K | 275 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) | Q2_K | 412 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 27B | Q2_K | 12.3 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q2_K | 15.2 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. | Ornith 1.5 122B-A10B | Q2_K | 50.9 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 Exp | Q2_K | 275 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. | Gemma 4 26B-A4B | Q2_K | 11.4 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 1T | Q2_K | 411 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) | Q2_K | 94.3 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-A9B | Q2_K | 30.7 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 (671B) | Q2_K | 270 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) | Q2_K | 117 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. | Muse Glimmer 30B | Q2_K | 12.7 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q2_K | 14.9 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-A10B | Q2_K | 50.9 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) | Q2_K | 80.9 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 Terminus | Q2_K | 275 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) | Q2_K | 275 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 31B | Q2_K | 14.8 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q2_K | 14.7 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Instruct 0905 (1T) | Q2_K | 412 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) | Q2_K | 32.1 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.1 (230B-A10B) | Q2_K | 94.3 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 2507 | Q2_K | 96.3 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-A35B | Q2_K | 195 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q2_K | 15.2 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2 Flash (309B-A15B) | Q2_K | 125 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q2_K | 16.8 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 1T | Q2_K | 403 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) | Q2_K | 271 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q2_K | 15.2 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Instruct 2507 | Q2_K | 96.3 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 250B | Q2_K | 102 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. | TMax 27B | Q2_K | 12.2 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q2_K | 15.2 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) | Q2_K | 412 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) | Q2_K | 94.3 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q2_K | 15.2 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 Instruct | Q2_K | 96.5 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. | Command A+ (218B-A25B) | Q2_K | 88.5 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. | Fara 1.5 27B | Q2_K | 12.2 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. | GLM-4.7 Flash (30B-A3B) | Q2_K | 13.6 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-A23B | Q2_K | 96.0 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | LongCat Flash Chat (560B) | Q2_K | 226 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-A12B | Q2_K | 50.2 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-A22B | Q2_K | 96.3 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. | Raon-1 mini Preview (30B-A4B) | Q2_K | 12.3 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 35B-A3B | Q2_K | 14.9 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. | Qwen AgentWorld 35B-A3B | Q2_K | 14.7 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Devstral 2 (123B) | Q2_K | 53.7 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 241B-A28B | Q2_K | 98.6 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. | Laguna S 2.1 (118B-A8B) | Q2_K | 49.3 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 v1 | Q2_K | 106 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) | Q2_K | 32.8 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q2_K | 33.4 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 27B | Q2_K | 12.2 GB | — | Won't run |
| 59Good quality (B) · 59 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 Hy-Memory 30B-A3B | Q2_K | 13.5 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-A22B | Q2_K | 96.3 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6 (355B-A32B) | Q2_K | 146 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 Instruct | Q2_K | 33.4 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) | Q2_K | 275 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. | Gemma 4 12B | Q2_K | 6.2 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6V | Q2_K | 45.3 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-M1 80K | Q2_K | 183 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) | Q2_K | 45.9 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.5 33B | Q2_K | 15.2 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) | Q2_K | 147 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Laguna XS 2.1 (33B-A3B) | Q2_K | 15.4 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. | Ling 3.0 Flash (127B-A5B) | Q2_K | 52.1 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 40K | Q2_K | 183 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) | Q2_K | 48.6 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 Medium 3.5 (128B) | Q2_K | 54.7 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Large Thinking (400B-A13B) | Q2_K | 161 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) | Q2_K | 45.9 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. | ERNIE 4.5 300B-A47B | Q2_K | 123 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-4.5V | Q2_K | 45.3 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 405B | Q2_K | 167 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. | K2 Horizon 7B | Q2_K | 5.5 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Dev 72B | Q2_K | 32.5 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 Flash (104B-A7.4B) | Q2_K | 43.7 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.3 Nemotron Super 49B v1.5 | Q2_K | 23.3 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2.1 (2411) | Q2_K | 52.7 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Cascade 2 30B-A3B | Q2_K | 13.4 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. | North Mini Code 1.0 (30B-A3B) | Q2_K | 13.2 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. | Seed-OSS 36B Instruct | Q2_K | 17.3 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 100B | Q2_K | 43.4 GB | — | Won't run |
| 55Good quality (B) · 55 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4.3 36B | Q2_K | 17.3 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | DiffusionGemma 26B-A4B IT | Q2_K | 11.4 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) | Q2_K | 46.4 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. | MiMo V2.6 Distill Qwen 9B | Q2_K | 4.7 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) | Q2_K | 52.8 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Pro | Q2_K | 160 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) | Q2_K | 53.2 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. | Qwen3 30B-A3B Thinking 2507 | Q2_K | 13.7 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. | Qwen3 Coder 30B-A3B | Q2_K | 13.7 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. | Qwen3-VL 32B Instruct | Q2_K | 16.2 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. | QwQ 32B | Q2_K | 15.9 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ring Flash 2.0 (100B-A6B) | Q2_K | 42.4 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. | SenseNova Loop 9B Preview | Q2_K | 5.0 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 30B-A3B | Q2_K | 13.4 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. | Ornith 1.5 9B | Q2_K | 4.8 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Instruct 2507 | Q2_K | 13.7 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. | Devstral Small 2 (24B) | Q2_K | 11.6 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | dots.llm1 Instruct | Q2_K | 66.1 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 30B | Q2_K | 14.6 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 38B | Q2_K | 18.2 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ling Flash 2.0 (100B-A6B) | Q2_K | 42.4 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-Text-01 | Q2_K | 183 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Think | Q2_K | 14.3 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 32B | Q2_K | 15.9 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 32B | Q2_K | 16.0 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 30B-A3B Thinking | Q2_K | 13.9 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q2_K | 4.8 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Skywork OR1 32B | Q2_K | 15.9 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 405B | Q2_K | 167 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) | Q2_K | 270 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. | Ornith 1.0 9B | Q2_K | 4.8 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 105B | Q2_K | 43.4 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 (236B) | Q2_K | 95.6 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 32B | Q2_K | 15.6 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 32B 0414 | Q2_K | 14.2 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. | GLM-Z1 32B (0414) | Q2_K | 14.2 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. | Hermes 4 70B | Q2_K | 31.6 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan A13B (80B-A13B) | Q2_K | 33.9 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. | InternVL3 78B | Q2_K | 34.7 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. | Kimi Linear 48B-A3B | Q2_K | 20.4 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Leanstral 119B-A6B | Q2_K | 48.6 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 24B-A2B | Q2_K | 10.5 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.3 70B Instruct | Q2_K | 31.6 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B | Q2_K | 13.7 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. | Qwen3-VL 30B-A3B Instruct | Q2_K | 13.9 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. | TMax 9B | Q2_K | 4.5 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 72B Instruct | Q2_K | 32.5 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 72B Instruct | Q2_K | 32.7 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. | Apriel 1.5 15B Thinker | Q2_K | 8.3 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Instruct (0614) | Q2_K | 95.6 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 70B | Q2_K | 31.6 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 32B | Q2_K | 16.0 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 1210 | Q2_K | 95.6 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 32B | Q2_K | 14.2 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 27B IT | Q2_K | 12.5 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 30B | Q2_K | 14.4 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 405B Instruct | Q2_K | 167 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) | Q2_K | 163 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-16E | Q2_K | 45.7 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. | Magistral Small 1.2 (24B) | Q2_K | 11.6 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Lightning 30B-A3B | Q2_K | 13.4 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Instruct | Q2_K | 14.3 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Plus (14B) | Q2_K | 8.2 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 70B | Q2_K | 31.6 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan M2 32B | Q2_K | 15.9 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) 104B | Q2_K | 44.4 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 | Q2_K | 95.6 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. | Devstral Small 1.1 (24B) | Q2_K | 11.5 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. | ERNIE 4.5 21B-A3B Thinking | Q2_K | 9.9 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 261023 | Q2_K | 48.2 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 38B | Q2_K | 18.2 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Large | Q2_K | 160 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 Instruct | Q2_K | 31.6 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. | Magistral Small 2507 | Q2_K | 11.5 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. | Maple Preview (20B-A1B) | Q2_K | 8.9 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. | MedGemma 27B Text IT | Q2_K | 12.3 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. | Mellum2.1 Thinking (12B-A2.5B) | Q2_K | 5.7 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. | Nemotron 3.5 Bolt E4B | Q2_K | 4.0 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | OpenHands LM 32B | Q2_K | 15.9 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. | Phi-4 Reasoning (14B) | Q2_K | 8.2 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Vision 15B | Q2_K | 8.4 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 32B Instruct | Q2_K | 16.0 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Omni 30B-A3B Instruct | Q2_K | 15.6 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. | Sarvam 30B | Q2_K | 13.7 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. | UI-Mate 9B | Q2_K | 4.7 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. | UI-Venus 2 9B | Q2_K | 4.7 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. | Gemma 4 E4B | Q2_K | 4.0 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. | Granite 4.2 8B | Q2_K | 5.6 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 70B) | Q2_K | 31.6 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 flash Sante | Q2_K | 51.8 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. | Magistral Small 2506 | Q2_K | 11.5 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.2 24B | Q2_K | 11.6 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q2_K | 3.8 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. | Nemotron Labs Dory 1.0 4B | Q2_K | 2.8 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 Preview | Q2_K | 32.7 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 32B Instruct | Q2_K | 16.2 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. | Qwen3 14B | Q2_K | 8.0 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. | Terminal RSI 27B | Q2_K | 12.3 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. | Hemmingway 1.5 | Q2_K | 12.0 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. | Qwen2.5 Coder 32B Instruct | Q2_K | 16.0 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. | AceReason Nemotron 14B | Q2_K | 8.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 70B | Q2_K | 32.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Apriel Nemotron 15B Thinker | Q2_K | 8.4 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2505 | Q2_K | 11.5 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. | Hermes 4 14B | Q2_K | 7.9 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 3.1 Nemotron 70B Instruct | Q2_K | 31.6 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 Instruct | Q2_K | 39.5 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. | Ministral 3 14B Reasoning | Q2_K | 7.6 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. | Mistral Small 3.1 24B | Q2_K | 11.6 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. | OpenReasoning Nemotron 14B | Q2_K | 8.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 14B Instruct | Q2_K | 8.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B Preview | Q2_K | 15.9 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. | Reka Flash 3.1 (21B) | Q2_K | 10.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova 6.8 Code2Video | Q2_K | 12.2 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q2_K | 2.6 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. | Trinity Mini (26B-A3B) | Q2_K | 11.3 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ 104B (04-2024) | Q2_K | 44.4 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. | DeepCoder 14B Preview | Q2_K | 8.2 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B | Q2_K | 9.9 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 34B Instruct | Q2_K | 15.4 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. | InternVL3 14B | Q2_K | 8.4 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. | Ministral 3 14B | Q2_K | 7.6 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. | Mistral Small 3 24B (2501) | Q2_K | 11.5 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. | Phi-4 (14B) | Q2_K | 8.3 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 72B Instruct | Q2_K | 32.5 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 Instruct | Q2_K | 32.7 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Axion 1.0 35B | Q2_K | 14.9 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. | Codestral 22B | Q2_K | 11.5 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Command R (08-2024) 32B | Q2_K | 15.0 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 R1 0528 Qwen3 8B | Q2_K | 5.2 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 R1 Distill Qwen 14B | Q2_K | 8.2 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 Chat | Q2_K | 95.6 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin Mistral 24B Venice Edition | Q2_K | 11.6 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 27B IT | Q2_K | 13.3 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. | Gemma 4 E2B | Q2_K | 2.8 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Small (32B-A9B) | Q2_K | 13.7 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. | InternVL3.5 8B | Q2_K | 5.3 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. | JanusCoder 14B | Q2_K | 7.9 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. | Qwen2.5 14B Instruct | Q2_K | 8.2 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. | Qwen3-VL 8B Instruct | Q2_K | 5.4 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. | Qwen3.5 4B | Q2_K | 2.8 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Small 24B | Q2_K | 11.7 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. | TMax 4B | Q2_K | 2.6 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. | Agents-A1 4B | Q2_K | 2.8 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 70B Instruct | Q2_K | 31.6 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 32B | Q2_K | 15.0 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 32B | Q2_K | 15.3 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. | Dolphin 3.0 R1 Mistral 24B | Q2_K | 11.5 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 12B IT | Q2_K | 6.2 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.1V 9B Thinking | Q2_K | 5.1 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. | Granite 4.1 8B | Q2_K | 5.6 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. | Kimi-VL A3B Thinking 2506 | Q2_K | 7.5 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q2_K | 4.1 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. | Mage-VL-Cowork 4.7B | Q2_K | 3.8 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.5 8B | Q2_K | 5.4 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q2_K | 2.1 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. | Nemotron Nano 9B v2 | Q2_K | 4.4 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 32B Instruct | Q2_K | 14.7 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. | Qwen2.5 14B Instruct 1M | Q2_K | 8.2 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 8B | Q2_K | 5.2 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Solar Pro Preview 22B | Q2_K | 10.9 GB | — | Won't run |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Mini | Q2_K | 14.9 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. | Fara 1.5 4B | Q2_K | 2.8 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 9B (0414) | Q2_K | 4.8 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 70B Instruct | Q2_K | 31.6 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. | LLM4Decompile 22B V2 | Q2_K | 11.5 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | MiMo-VL 7B RL | Q2_K | 5.2 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 Instruct | Q2_K | 31.1 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. | Seed-Coder 8B Reasoning | Q2_K | 5.1 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Groot 19B A3B 261023 | Q2_K | 8.6 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 7.8B | Q2_K | 4.9 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1R 7B | Q2_K | 4.1 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 8B | Q2_K | 4.3 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 24B-A2B | Q2_K | 10.4 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL 4.7B | Q2_K | 3.8 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | MiMo 7B RL | Q2_K | 5.0 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 8B | Q2_K | 5.4 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 MoE (42B-A6.6B) | Q2_K | 18.5 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Thinking 2507 | Q2_K | 3.5 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Instruct | Q2_K | 5.1 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 Instruct | Q2_K | 58.8 GB | — | Won't run |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 7B Instruct | Q2_K | 4.2 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) | Q2_K | 25.4 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. | Llama 3.1 Nemotron Nano 8B v1 | Q2_K | 5.0 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. | MiniCPM4 8B | Q2_K | 4.2 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. | Mistral Small 22B (2409) | Q2_K | 11.5 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. | Olmo 3 7B Think | Q2_K | 5.1 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. | OpenReasoning Nemotron 7B | Q2_K | 4.2 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. | Qwen3 4B Instruct 2507 | Q2_K | 3.5 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. | Qwen3-VL 4B Instruct | Q2_K | 3.7 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. | DeepSeek Coder V2 Lite (16B) | Q2_K | 7.2 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. | Falcon 3 10B Instruct | Q2_K | 6.2 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. | Foundation-Sec 8B Reasoning | Q2_K | 5.0 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. | GLM-4 9B 0414 | Q2_K | 4.8 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. | Granite 4.2 3B | Q2_K | 2.8 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. | Hunyuan 7B Instruct | Q2_K | 4.8 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. | LFM2.5 8B-A1B | Q2_K | 4.2 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. | Ling Mini 2.0 (16B-A1.4B) | Q2_K | 7.5 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. | MiniCPM-o 2.6 8B | Q2_K | 4.6 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. | Mistral Nemo 12B Instruct | Q2_K | 6.9 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. | NorthCUA Nano | Q2_K | 4.7 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. | Nous Hermes 2 Mixtral 8x7B DPO | Q2_K | 20.4 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 Chat | Q2_K | 47.9 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. | Qwen2.5 7B Instruct | Q2_K | 4.2 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. | Qwen2.5-VL 7B Instruct | Q2_K | 4.5 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 35B | Q2_K | 25.4 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. | DeepSeek R1 Distill Llama 8B | Q2_K | 5.0 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 7B Instruct | Q2_K | 4.1 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Fara 7B | Q2_K | 4.5 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. | Foundation-Sec 1.1 8B Instruct | Q2_K | 5.0 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 9B IT | Q2_K | 6.0 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 9B | Q2_K | 4.1 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Grok-1 (314B) | Q2_K | 128 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. | InternLM2.5 20B Chat | Q2_K | 10.3 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | InternLM3 8B Instruct | Q2_K | 4.6 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. | InternVL2.5 8B | Q2_K | 5.0 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Mini | Q2_K | 21.5 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. | Kimi-VL A3B Instruct | Q2_K | 7.5 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. | LFM3-VL 2B | Q2_K | 1.6 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x7B Instruct | Q2_K | 20.4 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. | Nemotron 3 Nano 4B | Q2_K | 2.4 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. | Olmo 3 7B Instruct | Q2_K | 5.1 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral 12B (2409) | Q2_K | 7.0 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qianfan-OCR 4B | Q2_K | 3.8 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 57B-A14B Instruct | Q2_K | 24.1 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct 1M | Q2_K | 4.2 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. | Qwen3 4B | Q2_K | 3.5 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 Instruct | Q2_K | 193 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 34B Chat | Q2_K | 15.5 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | Chandra OCR 2 | Q2_K | 3.1 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | GLM-4 9B Chat (2024) | Q2_K | 4.8 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | GLM-4 9B Chat 1M | Q2_K | 5.2 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | Hermes 3 (Llama 3.1 8B) | Q2_K | 5.0 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | LightOnOCR-3 4B | Q2_K | 2.8 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | Llama 3.1 8B Instruct | Q2_K | 5.0 GB | — | Won't run |
| 33Basic quality (D) · 33 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. | MiniCPM-V 2.6 8B | Q2_K | 4.4 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Apertus v1.5 8B | Q2_K | 5.3 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | CodeGeeX4 All 9B | Q2_K | 4.8 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | DeepHermes 3 Llama 3 8B Preview | Q2_K | 5.0 GB | — | Won't run |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 7B | Q2_K | 4.2 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Dolphin 3.0 Llama 3.1 8B | Q2_K | 5.0 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | EXAONE 3.5 7.8B | Q2_K | 4.9 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Falcon 3 7B Instruct | Q2_K | 4.6 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Gemma 3n E4B | Q2_K | 4.0 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Granite 3.2 8B Instruct | Q2_K | 5.3 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Granite 3.3 8B | Q2_K | 5.3 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Granite 4.1 3B | Q2_K | 2.7 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Ministral 8B (2410) | Q2_K | 5.1 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Moonlight 16B-A3B Instruct | Q2_K | 7.3 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Phi-3 Medium (14B) | Q2_K | 7.1 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Phi-3 Medium 128K Instruct | Q2_K | 8.0 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Phi-4 Mini Reasoning (3.8B) | Q2_K | 3.3 GB | — | Won't run |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 7B | Q2_K | 5.5 GB | — | Won't run |
| 32Basic quality (D) · 32 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. | Tülu 3 8B | Q2_K | 5.0 GB | — | Won't run |
| 31Basic quality (D) · 31 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. | Gemma 3 4B IT | Q2_K | 2.7 GB | — | Won't run |
| 31Basic quality (D) · 31 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. | WeVisOne-VL 4B | Q2_K | 3.8 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. | Aya Vision 8B | Q2_K | 4.5 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 70B Instruct | Q2_K | 29.6 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. | Command R7B | Q2_K | 4.3 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 33B Instruct | Q2_K | 16.1 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. | Dolphin 2.9.4 Llama 3.1 8B | Q2_K | 5.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 8B Instruct | Q2_K | 5.3 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Tiny (7B-A1B) | Q2_K | 3.5 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Llama 3 8B | Q2_K | 5.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2 8B | Q2_K | 5.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Jamba Reasoning 3B | Q2_K | 2.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | Q2_K | 1.9 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. | LFM2.5-VL 3B | Q2_K | 2.1 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. | Llama 3.1 Nemotron Nano 4B v1.1 | Q2_K | 3.6 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 34B | Q2_K | 15.6 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. | MedGemma 4B IT | Q2_K | 2.7 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. | Ministral 3 3B | Q2_K | 3.1 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. | North Micro Vision | Q2_K | 2.6 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. | OLMo 2 13B Instruct | Q2_K | 9.5 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.6 8B | Q2_K | 5.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Small 8K Instruct | Q2_K | 4.7 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. | Phi-4 Mini (3.8B) | Q2_K | 3.3 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Multimodal Instruct | Q2_K | 4.0 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 32B Chat | Q2_K | 15.8 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. | Qwen2 7B Instruct | Q2_K | 4.2 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. | Qwen2-VL 7B Instruct | Q2_K | 4.5 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q2_K | 2.5 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | Command R7B Arabic | Q2_K | 4.3 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | Hunyuan 4B Instruct | Q2_K | 3.6 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | InternLM2 Chat 20B | Q2_K | 10.3 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | Jamba2 3B | Q2_K | 1.9 GB | — | Won't run |
| 29Basic quality (D) · 29 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 3 8B Instruct | Q2_K | 5.0 GB | — | Won't run |
| 29Basic quality (D) · 29 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 3.2 11B Vision Instruct | Q2_K | 6.3 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | Mistral-NeMo-Minitron 8B Instruct | Q2_K | 5.4 GB | — | Won't run |
| 29Basic quality (D) · 29 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. | SmolLM3 3B | Q2_K | 2.5 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. | AFM 4.5B | Q2_K | 3.1 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 8B Instruct | Q2_K | 5.0 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. | Aya Expanse 8B | Q2_K | 5.0 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 Chat | Q2_K | 29.2 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 Prover V2 7B | Q2_K | 7.5 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 V2 Lite Chat | Q2_K | 7.2 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 8B Instruct | Q2_K | 4.6 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 Micro (3B) | Q2_K | 2.7 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 34B Instruct | Q2_K | 14.6 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. | InternLM2 Math Plus 20B | Q2_K | 10.3 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. | InternLM2.5 7B Chat | Q2_K | 4.9 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. | Nous Hermes 2 SOLAR 10.7B | Q2_K | 5.8 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. | Phi-3.5 Mini Instruct | Q2_K | 5.4 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 2B | Q2_K | 1.7 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | SOLAR 10.7B Instruct | Q2_K | 5.8 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. | StarCoder2 15B Instruct | Q2_K | 7.8 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. | TeleOCR | Q2_K | 2.2 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. | TMax 2B | Q2_K | 1.5 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. | Unlimited OCR (3B-A0.6B) | Q2_K | 2.5 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Yi 34B Chat | Q2_K | 15.5 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 9B Chat | Q2_K | 5.0 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 34B Instruct | Q2_K | 15.8 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | CogVLM2 Llama 3 Chat 19B | Q2_K | 12.8 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9 Llama 3 8B | Q2_K | 5.0 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.0 7.8B Instruct | Q2_K | 4.4 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Falcon3 Mamba 7B Instruct | Q2_K | 3.6 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Micro | Q2_K | 2.0 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 8B-A1B | Q2_K | 4.1 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 9B V2 | Q2_K | 5.0 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM3 4B | Q2_K | 2.6 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.3 | Q2_K | 4.7 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Vision Instruct | Q2_K | 5.6 GB | — | Won't run |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 7B Instruct | Q2_K | 4.4 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. | S5 nano | Q2_K | 2.8 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. | Codestral Mamba 7B | Q2_K | 3.6 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. | Falcon-H1 3B Instruct | Q2_K | 2.2 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. | Gemma 3n E2B | Q2_K | 3.0 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. | Granite Code 20B Instruct | Q2_K | 8.9 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. | Hermes 2 Pro Mistral 7B | Q2_K | 4.7 GB | — | Won't run |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 70B Chat | Q2_K | 29.6 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. | OLMo 2 7B Instruct | Q2_K | 5.8 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. | Phi-3 Mini 128K Instruct | Q2_K | 5.4 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. | Phi-3 Mini 4K Instruct | Q2_K | 3.8 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. | Qwen2.5 Coder 3B Instruct | Q2_K | 2.2 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. | Qwen2.5-Math 7B Instruct | Q2_K | 4.0 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. | Qwen3-VL 2B Instruct | Q2_K | 2.5 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. | Starling LM 7B Beta | Q2_K | 4.7 GB | — | Won't run |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Mini 3B | Q2_K | 3.6 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. | Yi 1.5 9B Chat | Q2_K | 4.6 GB | — | Won't run |
| 24Basic quality (D) · 24 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 3.2 3B Instruct | Q2_K | 2.9 GB | — | Won't run |
| 24Basic quality (D) · 24 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. | OpenChat 3.5 (0106) | Q2_K | 4.7 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. | Aya 23 8B | Q2_K | 5.0 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. | CodeGemma 7B | Q2_K | 7.9 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. | DeepSeek Coder 6.7B Instruct | Q2_K | 7.7 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 Chat | Q2_K | 72.8 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. | LFM2 2.6B | Q2_K | 1.9 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. | Mathstral 7B | Q2_K | 4.7 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. | Mistral 7B Instruct v0.2 | Q2_K | 4.7 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. | Nous Hermes 2 Mistral 7B DPO | Q2_K | 4.7 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. | OpenChat 3.5 (1210) | Q2_K | 4.7 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. | Phi-3 Vision 128K Instruct | Q2_K | 5.6 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 Chat | Q2_K | 13.1 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. | Qwen2.5 3B Instruct | Q2_K | 2.2 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. | Qwen2.5-VL 3B Instruct | Q2_K | 2.5 GB | — | Won't run |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | RecurrentGemma 9B IT | Q2_K | 4.7 GB | — | Won't run |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 8B Instruct (128K) | Q2_K | 5.1 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | Hermes 3 Llama 3.2 3B | Q2_K | 2.9 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | InternLM2 Math Plus 7B | Q2_K | 4.9 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | LLM4Decompile 6.7B V2 | Q2_K | 7.7 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | OpenHermes 2.5 Mistral 7B | Q2_K | 4.7 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | StarCoder2 15B (base) | Q2_K | 7.8 GB | — | Won't run |
| 22Basic quality (D) · 22 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. | Starling LM 7B Alpha | Q2_K | 4.7 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 Instruct | Q2_K | 12.6 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. | EXAONE 3.5 2.4B | Q2_K | 2.3 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. | EXAONE 4.0 1.2B | Q2_K | 1.7 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. | Falcon 3 3B Instruct | Q2_K | 2.7 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. | Falcon Mamba 7B Instruct | Q2_K | 3.6 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. | Granite 3.2 2B Instruct | Q2_K | 2.4 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. | Granite 3.3 2B | Q2_K | 2.4 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. | Mistral 7B Instruct v0.1 | Q2_K | 4.7 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. | Qwen2.5-Omni 3B | Q2_K | 3.2 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. | Qwen3 1.7B | Q2_K | 2.4 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. | SQLCoder 7B v2 | Q2_K | 7.7 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Gemma 1.1 7B IT | Q2_K | 7.9 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Gemma 2 2B | Q2_K | 2.2 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Granite 3.1 2B Instruct | Q2_K | 2.4 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | LLaVA 1.6 Mistral 7B | Q2_K | 4.8 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Neural Chat 7B v3.3 | Q2_K | 4.7 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Orca 2 13B | Q2_K | 9.3 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | StableLM 2 12B Chat | Q2_K | 6.4 GB | — | Won't run |
| 19Basic quality (D) · 19 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. | Yi 1.5 6B Chat | Q2_K | 3.4 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | WeVisOne VL 2B | Q2_K | 2.6 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Baichuan 2 13B Chat | Q2_K | 9.6 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | DeepScaleR 1.5B Preview | Q2_K | 1.6 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | DeepSeek MoE 16B Chat | Q2_K | 8.2 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Falcon-H1 1.5B Instruct | Q2_K | 1.5 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Gemma 7B IT | Q2_K | 7.9 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Granite 3.0 2B Instruct | Q2_K | 2.1 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Granite Vision 3.2 2B | Q2_K | 2.6 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Llama 2 13B Chat | Q2_K | 9.3 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | OLMoE 1B-7B Instruct | Q2_K | 4.0 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Qwen1.5 7B Chat | Q2_K | 8.1 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Qwen2.5 Coder 1.5B Instruct | Q2_K | 1.5 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | StarCoder 15B | Q2_K | 7.2 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | WizardMath 7B v1.1 | Q2_K | 4.7 GB | — | Won't run |
| 18Basic quality (D) · 18 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. | Zephyr 7B Beta | Q2_K | 4.7 GB | — | Won't run |
| 16Basic quality (D) · 16 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 7B Instruct | Q2_K | 7.7 GB | — | Won't run |
| 16Basic quality (D) · 16 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. | Qwen1.5 MoE A2.7B Chat | Q2_K | 8.0 GB | — | Won't run |
| 16Basic quality (D) · 16 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. | Qwen2-VL 2B Instruct | Q2_K | 1.8 GB | — | Won't run |
| 16Basic quality (D) · 16 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. | Qwen2.5 1.5B Instruct | Q2_K | 1.5 GB | — | Won't run |
| 16Basic quality (D) · 16 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. | SmolVLM2 2.2B Instruct | Q2_K | 3.2 GB | — | Won't run |
| 16Basic quality (D) · 16 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. | StarCoder2 7B | Q2_K | 4.1 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | DeepSeek R1 Distill Qwen 1.5B | Q2_K | 1.6 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | Hunyuan 1.8B Instruct | Q2_K | 1.9 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | LLaVA 1.5 13B | Q2_K | 9.4 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | Nemotron Mini 4B Instruct | Q2_K | 2.9 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | Orca 2 7B | Q2_K | 5.5 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | SmolVLM 2.2B Instruct | Q2_K | 3.2 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | WizardLM 13B v1.2 | Q2_K | 9.3 GB | — | Won't run |
| 15Basic quality (D) · 15 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. | Zamba2 2.7B Instruct | Q2_K | 2.1 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | d1 2B | Q2_K | 1.6 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 7B Chat | Q2_K | 5.8 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 3B-A800M Instruct | Q2_K | 2.6 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 3B Instruct (128K) | Q2_K | 4.8 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 7B Chat | Q2_K | 5.5 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 1.7B Instruct | Q2_K | 3.0 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Stable Code Instruct 3B | Q2_K | 4.5 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 13B v1.5 | Q2_K | 9.3 GB | — | Won't run |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Yi 6B Chat | Q2_K | 3.4 GB | — | Won't run |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek LLM 7B Chat | Q2_K | 5.5 GB | — | Won't run |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 3B-A800M Instruct | Q2_K | 2.3 GB | — | Won't run |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 1.8B Chat | Q2_K | 2.3 GB | — | Won't run |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 3B | Q2_K | 2.2 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 2B | Q2_K | 1.5 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 1B Instruct | Q2_K | 2.0 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 40B Instruct | Q2_K | 17.7 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 7B | Q2_K | 5.7 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Phi-2 2.7B | Q2_K | 2.5 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 1.5B Instruct | Q2_K | 1.5 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | StableLM Zephyr 3B | Q2_K | 3.2 GB | — | Won't run |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 1.5B Chat | Q2_K | 2.9 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | CodeGemma 2B | Q2_K | 1.9 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 1B Instruct | Q2_K | 1.8 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 7B Instruct | Q2_K | 4.5 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 0.6B | Q2_K | 1.9 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 1.7B Instruct | Q2_K | 1.8 GB | — | Won't run |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 7B v1.5 | Q2_K | 5.5 GB | — | Won't run |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 1.3B Instruct | Q2_K | 2.8 GB | — | Won't run |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2B IT | Q2_K | 1.9 GB | — | Won't run |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | InternLM 7B | Q2_K | 4.7 GB | — | Won't run |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 1/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 1.3B V2 | Q2_K | 2.8 GB | — | Won't run |
| 7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 0/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 1.6B Chat | Q2_K | 2.2 GB | — | Won't run |
| 7Basic quality (D) · 7 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 0/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 Zephyr 1.6B | Q2_K | 2.2 GB | — | Won't run |
| 5Basic quality (D) · 5 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 0/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 0.5B Instruct | Q2_K | 1.7 GB | — | Won't run |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 0/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 7B Instruct | Q2_K | 3.6 GB | — | Won't run |
Image models on the Raspberry Pi 4 (2 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 Dev | FP16 | 8.1 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. | Krea 2 Turbo | FP8 | 7.1 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) | FP8 | 26.1 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) | FP8 | 32.8 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 2.1 | Q4 GGUF | 26.0 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-Image | FP8 | 13.3 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] | Q4 GGUF | 10.1 GB | — | Won't run |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | NF4 | 6.1 GB | — | Won't run |
| 84Great quality (A) · 84 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 3 Image Klein | Q4 GGUF | 3.4 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 Design | FP8 | 16.4 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 2512 | Q4 GGUF | 10.4 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 Turbo | Q4 GGUF | 15.7 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. | ERNIE-Image | Q4 GGUF | 4.1 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 1.1 | Q4 GGUF | 7.8 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 2511 | Q4 GGUF | 7.8 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. | ERNIE-Image Turbo | Q4 GGUF | 4.1 GB | — | Won't run |
| 78Great quality (A) · 78 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. | FLUX.2 [klein] 9B | Q4 GGUF | 4.3 GB | — | Won't run |
| 78Great quality (A) · 78 of 100: how capable the model is at NF4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Full | NF4 | 6.2 GB | — | Won't run |
| 78Great quality (A) · 78 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. | Z-Image Turbo | Q4 GGUF | 3.5 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. | FLUX.1 Kontext [dev] | Q4 GGUF | 5.8 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. | FLUX.1 Krea [dev] | Q4 GGUF | 5.1 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. | MOSS-Image SFT | Q4 GGUF | 3.3 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. | Z-Image | Q4 GGUF | 3.5 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. | FLUX.1 Fill [dev] | FP8 | 6.8 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [dev] | NF4 | 5.0 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Dev | NF4 | 6.2 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at NF4, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Chroma1-HD | NF4 | 4.3 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. | FLUX.2 [klein] 4B | Q4 GGUF | 2.9 GB | — | Won't run |
| 72Great quality (A) · 72 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. | Iris-3B | FP16 | 4.5 GB | — | Won't run |
| 70Great quality (A) · 70 of 100: how capable the model is at NF4, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Fast | NF4 | 6.2 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. | CogView4 6B | FP8 | 4.4 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at NF4, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [schnell] | NF4 | 5.0 GB | — | Won't run |
| 64Good quality (B) · 64 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. | OmniGen2 | FP8 | 3.8 GB | — | Won't run |
| 61Good quality (B) · 61 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. | Stable Diffusion 3.5 Large | Q4 GGUF | 4.1 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. | Juggernaut XL v9 | FP8 | 2.9 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. | Lumina-Image 2.0 | FP8 | 3.0 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. | RealVisXL V5.0 | FP8 | 2.9 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. | Animagine XL 4.0 | FP8 | 2.9 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. | Illustrious XL v0.1 | FP8 | 2.9 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. | Kolors | FP8 | 2.9 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. | Playground v2.5 | FP8 | 2.9 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Large Turbo | Q4 GGUF | 4.1 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. | DreamShaper XL v2 Turbo | FP8 | 2.9 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. | Pony Diffusion V6 XL | FP8 | 2.9 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. | Stable Diffusion 3.5 Medium | FP8 | 3.0 GB | — | Won't run |
| 54Fair quality (C) · 54 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. | Animagine XL 3.1 | FP8 | 2.9 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | AuraFlow v0.3 | Q4 GGUF | 3.7 GB | — | Won't run |
| 53Fair quality (C) · 53 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. | Stable Diffusion XL 1.0 | FP8 | 2.9 GB | — | Won't run |
| 52Fair quality (C) · 52 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. | SDXL-Lightning (4-step) | FP8 | 2.9 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. | Hunyuan-DiT v1.2 | FP16 | 3.1 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. | Stable Cascade | FP8 | 4.0 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. | Stable Diffusion 3 Medium | FP8 | 2.8 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | PixArt-Σ XL 1024 | FP16 | 2.3 GB | — | Won't run |
| 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 3 | FP16 | 4.2 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 1.3 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 1.3 GB | — | Won't run |
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 1.6 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 1.3 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 1.3 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 1.3 GB | — | Won't run |
Video models on the Raspberry Pi 4 (2 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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) | FP16 | 53.7 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) | FP16 | 27.8 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) | Q4 GGUF | 19.6 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) | FP8 | 10.7 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) | FP8 | 23.9 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) | Q4 GGUF | 16.8 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-2.3 | Q4 GGUF | 16.4 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 A14B | Q4 GGUF | 21.3 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 A14B | Q4 GGUF | 21.3 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) | FP8 | 12.5 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 720P | FP8 | 26.0 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) | Q4 GGUF | 16.4 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) | FP8 | 7.8 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) | FP8 | 25.0 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) | FP8 | 35.6 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 720P | Q4 GGUF | 21.3 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 14B | Q4 GGUF | 21.3 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 14B | Q4 GGUF | 22.0 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 14B | Q4 GGUF | 21.3 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) | FP8 | 10.8 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 540P | FP8 | 14.2 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) | Q4 GGUF | 9.0 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) | FP16 | 19.3 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 480P | Q4 GGUF | 8.5 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 Video2World | FP8 | 24.7 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) | FP16 | 8.9 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 13B | Q4 GGUF | 24.8 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 13B | Q4 GGUF | 24.8 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) | FP8 | 16.1 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 5B | Q4 GGUF | 21.4 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) | FP8 | 14.7 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 Text2World | FP16 | 29.2 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 5B | FP8 | 31.2 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 Video2World | FP8 | 20.5 GB | — | Won't run |
| 53Fair quality (C) · 53 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 5B | FP8 | 5.9 GB | — | Won't run |
| 53Fair quality (C) · 53 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 5B I2V | FP8 | 6.1 GB | — | Won't run |
| 53Fair quality (C) · 53 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. | Wan 2.1 T2V 1.3B | FP8 | 6.0 GB | — | Won't run |
| 53Fair quality (C) · 53 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. | Wan 2.1 VACE 1.3B | FP8 | 6.3 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) | FP16 | 24.7 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 1.3B | FP8 | 9.8 GB | — | Won't run |
| 49Fair quality (C) · 49 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. | LTX-Video 2B | FP8 | 4.0 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 4.7 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 2.6 GB | — | Won't run |
Decision models on the Raspberry Pi 4 (2 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 5.2 s | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass ModernBERT Large v3 | Q8_0 | 1.1 GB | 3.7 s | Very slowtight fit |
| 68Good quality (B) · 68 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 1.3 s | Slow |
| 75Great quality (A) · 75 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. | mxbai-rerank-base v2 | Q6_K | 1.1 GB | 8.5 s | Very slowtight fit |
| 70Great quality (A) · 70 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. | GTE Reranker ModernBERT Base | Q8_0 | 0.8 GB | 2.8 s | Very slow |
| 72Great quality (A) · 72 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. | DeBERTa v3 Large Zero-shot v2.0 | Q8_0 | 1.2 GB | 4.1 s | Very slowtight fit |
| 70Great quality (A) · 70 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. | Jina Reranker v2 Base Multilingual | Q8_0 | 1.0 GB | 5.2 s | Very slow |
| 68Good quality (B) · 68 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 Embedding Reranker English R2 | Q8_0 | 0.8 GB | 2.8 s | Very slow |
| 66Good quality (B) · 66 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. | GLiClass Base v3 | Q8_0 | 0.8 GB | 1.8 s | Very slow |
| 68Good quality (B) · 68 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. | GLiGuard 300M | Q8_0 | 0.9 GB | 3.9 s | Very slow |
| 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | ModernBERT Large Zero-shot v2.0 | Q8_0 | 1.1 GB | 3.7 s | Very slowtight fit |
| 64Good quality (B) · 64 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. | DeBERTa v3 Base Zero-shot v2.0 | Q8_0 | 0.8 GB | 1.7 s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | ProtectAI DeBERTa v3 Prompt Injection v2 | Q8_0 | 0.8 GB | 3.3 s | Very slow |
| 68Good quality (B) · 68 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. | Laya | Q8_0 | 1.2 GB | 3.9 s | Very slowtight fit |
| 68Good quality (B) · 68 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. | GLiNER2 Base v1 | Q8_0 | 0.9 GB | 2.0 s | Very slow |
| 52Fair quality (C) · 52 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. | ms-marco MiniLM L6 v2 | Q8_0 | 0.6 GB | 431 ms | Slow |
| 62Good quality (B) · 62 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. | HHEM 2.1 Open | Q8_0 | 0.7 GB | 4.1 s | Very slow |
| 60Good quality (B) · 60 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. | Laya Multilingual | Q8_0 | 1.0 GB | 3.0 s | Very slow |
| 62Good quality (B) · 62 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. | GLiNER Multi v2.1 | Q8_0 | 1.0 GB | 2.7 s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | LettuceDetect Large | Q8_0 | 1.1 GB | 14.8 s | Very slowtight fit |
| 56Good quality (B) · 56 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | BART Large MNLI | Q8_0 | 1.1 GB | 3.8 s | Very slowtight fit |
| 81Great quality (A) · 81 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. | Jina Reranker v3.5 | Q4_K_M | 1.3 GB | 10.4 s | Very slowover memory limit |
| 79Great quality (A) · 79 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. | Jina Reranker v3 | Q4_K_M | 1.3 GB | 10.4 s | Very slowover memory limit |
| 76Great quality (A) · 76 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. | Qwen3 Reranker 0.6B | Q4_K_M | 1.3 GB | 10.4 s | Very slowover memory limit |
| 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 0.6B | Q5_K_M | 1.5 GB | 13.8 s | Very slowfar over memory limit |
| 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 8B | Q8_0 | 10.4 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 27B | Q8_0 | 34.8 GB | — | Won't run |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q4_K_M | 3.5 GB | — | Won't run |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q4_K_M | 6.0 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 8B | Q8_0 | 10.5 GB | — | Won't run |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q4_K_M | 3.5 GB | — | Won't run |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 32B | Q4_K_M | 21.2 GB | — | Won't run |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 8B | Q4_K_M | 6.0 GB | — | Won't run |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q4_K_M | 3.3 GB | — | Won't run |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | Q8_0 | 1.7 GB | — | Won't run |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 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 120B | MXFP4 | 67.4 GB | — | Won't run |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | LemonDecider 4B | Q8_0 | 6.5 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 4.1 8B | Q4_K_M | 6.1 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q4_K_M | 3.5 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Safety Guard 8B v3 | Q4_K_M | 5.9 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 4B | Q4_K_M | 3.7 GB | — | Won't run |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | — | Won't run |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | Q4_K_M | 2.6 GB | — | Won't run |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q4_K_M | 1.7 GB | — | Won't run |
| 76Great quality (A) · 76 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 20B | MXFP4 | 13.0 GB | — | Won't run |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 3.3 8B | Q4_K_M | 6.0 GB | — | Won't run |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Selene 1 Mini 8B | Q4_K_M | 5.9 GB | — | Won't run |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | WildGuard 7B | Q4_K_M | 5.4 GB | — | Won't run |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | zerank-1 small | Q4_K_M | 2.0 GB | — | Won't run |
| 75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | DynaGuard 8B | Q4_K_M | 6.0 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 Gemma | Q4_K_M | 2.3 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 7B | Q4_K_M | 5.5 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Content Safety Reasoning 4B | Q4_K_M | 3.6 GB | — | Won't run |
| 72Great quality (A) · 72 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. | NuExtract 2.0 4B | Q4_K_M | 3.1 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 M3 | Q8_0 | 1.3 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | DuoGuard 0.5B | Q8_0 | 1.2 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 0.6B | Q8_0 | 1.4 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 8x7B | Q4_K_M | 29.5 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DynaGuard 1.7B | Q4_K_M | 2.2 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | NuExtract 2.0 2B | Q4_K_M | 2.1 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 8B | Q4_K_M | 5.9 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Prometheus 2 7B | Q4_K_M | 5.4 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | GLIDER | Q4_K_M | 3.8 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 4 12B | Q4_K_M | 8.4 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 27B | Q4_K_M | 18.1 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Flow Judge v0.1 | Q4_K_M | 3.8 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 9B | Q4_K_M | 7.0 GB | — | Won't run |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 2B | Q4_K_M | 2.5 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 1B | Q4_K_M | 1.7 GB | — | Won't run |
Upgrade picks
GPUs that would run more LLMs without offloading, at launch prices. Right now 23 of 619 LLMs run well on your Raspberry Pi 4 (2 GB).
Biggest jump
NVIDIA RTX PRO 6000 Blackwell
+523 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.