./models·full catalog · 145 modelssidebar drives compatibility math · pick a GPU or use detected
browse
every curated GGUF in the index
sort by grade · vram · fit · throughput · downloads · params · arch
runnable135
marginal2
no-go8
./models·compatibility matrix · 145/145sorted by fit desc
| grade | model | params | vram | fit ↓ | tok/s | weights | dl/mo | ctx | arch |
|---|---|---|---|---|---|---|---|---|---|
| S | Whisper Tiny English (Quantized) | 0.039B | 0.1GB | 10080 | 32.2 MB | 90.7k | — | whisper | |
| S | all-MiniLM-L6-v2 | 0.023B | 0.1GB | 10080 | 23.0 MB | 259.2M | 256 | bert | |
| S | BGE Small EN v1.5 | 0.033B | 0.1GB | 10080 | 36.8 MB | 42.6M | 512 | bert | |
| S | Snowflake Arctic Embed S | 0.033B | 0.1GB | 10080 | 36.0 MB | 42.2k | 512 | bert | |
| S | Piper TTS - Amy (English) | 0.02B | 0.1GB | 10080 | 63.1 MB | 0 | — | piper | |
| S | Piper TTS - Lessac (English) | 0.02B | 0.1GB | 10080 | 63.2 MB | 0 | — | piper | |
| S | Piper TTS - Spanish (MLS) | 0.02B | 0.1GB | 10080 | 63.1 MB | 0 | — | piper | |
| S | Piper TTS - German (Thorsten) | 0.02B | 0.1GB | 10080 | 63.1 MB | 0 | — | piper | |
| S | Piper TTS - Chinese (Huayan) | 0.02B | 0.1GB | 10080 | 63.2 MB | 0 | — | piper | |
| S | Piper TTS - Japanese (Kokoro) | 0.02B | 0.1GB | 10080 | 63.0 MB | 0 | — | piper | |
| S | Piper TTS - Korean | 0.02B | 0.1GB | 10080 | 63.0 MB | 0 | — | piper | |
| S | Piper TTS - Russian (Irina) | 0.02B | 0.1GB | 10080 | 63.2 MB | 0 | — | piper | |
| S | Piper TTS - Portuguese (Faber) | 0.02B | 0.1GB | 10080 | 63.2 MB | 0 | — | piper | |
| S | Piper TTS - Arabic (Kareem) | 0.02B | 0.1GB | 10080 | 63.2 MB | 0 | — | piper | |
| S | Jina Reranker Tiny EN | 0.033B | 0.1GB | 10080 | 67.5 MB | 100k | 8.2k | bert | |
| S | Whisper Tiny | 0.039B | 0.2GB | 10080 | 77.7 MB | 767.6k | — | whisper | |
| S | Whisper Base | 0.074B | 0.3GB | 10080 | 148.0 MB | 1.6M | — | whisper | |
| S | Whisper Base English | 0.074B | 0.3GB | 10080 | 148.0 MB | 36.4k | — | whisper | |
| S | Nomic Embed Text v1.5 | 0.137B | 0.3GB | 10080 | 146.1 MB | 16.1M | 8.2k | nomic-bert | |
| S | Piper TTS - French (Siwis) | 0.02B | 0.5GB | 10080 | 28.1 MB | 0 | — | piper | |
| S | Piper TTS - Italian (Riccardo) | 0.02B | 0.5GB | 10080 | 28.1 MB | 0 | — | piper | |
| S | Piper TTS - LibriTTS-R (English) | 0.02B | 0.6GB | 10080 | 78.6 MB | 0 | — | piper | |
| S | Kokoro 82M TTS | 0.082B | 0.6GB | 10080 | 86.0 MB | 310.1k | — | kokoro | |
| S | SmolLM2 135M | 0.135B | 0.6GB | 10080 | 144.8 MB | 1.6M | 8.2k | smollm | |
| S | SmolLM2 360M | 0.36B | 0.8GB | 5000 | 270.6 MB | 188.9k | 8.2k | smollm | |
| S | MusicGen Small | 0.3B | 0.8GB | 6000 | 302.4 MB | 124.6k | — | musicgen | |
| S | Danube 3 500M | 0.5B | 0.8GB | 3600 | 317.9 MB | 22.8k | 8.2k | danube | |
| S | BGE Large EN v1.5 | 0.335B | 0.8GB | 5373 | 358.2 MB | 15.4M | 512 | bert | |
| S | Whisper Small | 0.24B | 0.9GB | 7500 | 487.6 MB | 2.3M | — | whisper | |
| S | Qwen 2.5 0.5B | 0.5B | 1.0GB | 3600 | 491.4 MB | 5.6M | 32.8k | qwen2 | |
| S | TinyLlama 1.1B | 1.1B | 1.1GB | 1636 | 668.8 MB | 2.8M | 2k | llama | |
| S | Qwen 2.5 Coder 0.5B | 0.5B | 1.1GB | 3600 | 675.7 MB | 105.9k | 32.8k | qwen2 | |
| S | Llama 3.2 1B Instruct | 1.24B | 1.3GB | 1452 | 807.7 MB | 7.5M | 131.1k | llama | |
| S | Gemma 3 1B | 1B | 1.3GB | 1800 | 806.1 MB | 657.3k | 32.8k | gemma3 | |
| S | Granite 3.0 1B-A400M | 1.3B | 1.3GB | 4500 | 821.8 MB | 1.5k | 4.1k | granitemoe | |
| S | DeepSeek Coder 1.3B | 1.3B | 1.3GB | 1385 | 873.6 MB | 39.5k | 16.4k | llama | |
| S | Yi Coder 1.5B | 1.5B | 1.4GB | 1200 | 963.7 MB | 469 | 4.1k | yi | |
| S | Qwen2-VL 2B | 2.2B | 1.4GB | 818 | 986.0 MB | 4.3M | 32.8k | qwen2-vl | |
| S | SmolLM2 1.7B | 1.7B | 1.5GB | 1059 | 1.06 GB | 146.8k | 8.2k | smollm | |
| S | Falcon 3 1B | 1B | 1.5GB | 1800 | 1.06 GB | 11.8k | 8.2k | falcon | |
| S | Moondream 2 | 1.8B | 1.5GB | 1000 | 1.00 GB | 2.8M | 2k | moondream | |
| S | Qwen 2.5 1.5B | 1.5B | 1.5GB | 1200 | 1.12 GB | 12.1M | 32.8k | qwen2 | |
| S | DeepSeek R1 Distill 1.5B | 1.5B | 1.5GB | 1200 | 1.12 GB | 535.7k | 131.1k | qwen2 | |
| S | Qwen 2.5 Coder 1.5B | 1.5B | 1.5GB | 1200 | 1.12 GB | 340.7k | 32.8k | qwen2 | |
| S | Stable Diffusion 2.1 Base (CoreML) | 0.86B | 1.6GB | 2093 | 1.14 GB | 99 | — | unet-diffusion | |
| S | BGE Reranker v2 M3 | 0.568B | 1.6GB | 3169 | 1.16 GB | 11M | 8.2k | xlm-roberta | |
| S | Distil-Whisper Large v3 | 0.76B | 1.9GB | 2368 | 1.52 GB | 1.4M | — | whisper | |
| S | Whisper Medium | 0.77B | 1.9GB | 2338 | 1.53 GB | 888.3k | — | whisper | |
| S | Granite 3.3 2B | 2B | 1.9GB | 900 | 1.55 GB | 32.4k | 8.2k | granite | |
| S | Whisper Large v3 Turbo | 0.81B | 2.0GB | 2222 | 1.62 GB | 7.2M | — | whisper | |
| S | CodeGemma 2B | 2B | 2.0GB | 900 | 1.63 GB | 26.4k | 8.2k | gemma | |
| S | EXAONE 3.5 2.4B | 2.4B | 2.0GB | 750 | 1.64 GB | 28.5k | 32.8k | exaone | |
| S | Gemma 2 2B | 2.6B | 2.1GB | 692 | 1.71 GB | 377.9k | 8.2k | gemma2 | |
| S | StableLM Zephyr 3B | 3B | 2.1GB | 600 | 1.71 GB | 33.2k | 4.1k | stablelm | |
| S | Rocket 3B | 3B | 2.1GB | 600 | 1.71 GB | 379 | 4.1k | stablelm | |
| S | Stable Code 3B | 3B | 2.1GB | 600 | 1.71 GB | 2.1k | 16.4k | stablelm | |
| S | MiniCPM-V 2.6 | 2B | 2.1GB | 900 | 1.60 GB | 109.2k | 2k | minicpm-v | |
| S | Stable Diffusion 1.5 (GGUF) | 0.86B | 2.1GB | 2093 | 1.75 GB | 1.1k | — | unet-diffusion | |
| S | StarCoder2 3B | 3B | 2.3GB | 600 | 1.89 GB | 107.9k | 16.4k | starcoder | |
| S | Falcon 3 3B | 3B | 2.4GB | 600 | 2.01 GB | 6.8k | 8.2k | falcon | |
| S | Llama 3.2 3B Instruct | 3.2B | 2.4GB | 562 | 2.02 GB | 2.4M | 131.1k | llama | |
| S | Granite 3.0 3B-A800M | 3.4B | 2.4GB | 2250 | 2.06 GB | 2.2k | 4.1k | granitemoe | |
| S | Qwen 2.5 3B | 3B | 2.5GB | 600 | 2.10 GB | 8.1M | 32.8k | qwen2 | |
| S | Qwen 2.5 Coder 3B | 3B | 2.5GB | 600 | 2.10 GB | 409.2k | 32.8k | qwen2 | |
| S | Stable Diffusion 1.5 (CoreML) | 0.86B | 2.5GB | 2093 | 1.57 GB | 1.7M | — | unet-diffusion | |
| S | PaliGemma 3B | 3B | 2.5GB | 600 | 2.00 GB | 220.4k | 256 | paligemma | |
| S | Stable Diffusion 2.1 (GGUF) | 0.86B | 2.7GB | 2093 | 2.32 GB | — | — | unet-diffusion | |
| S | Phi-3.5 Mini 3.8B | 3.8B | 2.7GB | 474 | 2.39 GB | 776.5k | 131.1k | phi3 | |
| S | Danube 3 4B | 4B | 2.7GB | 450 | 2.39 GB | 746 | 8.2k | danube | |
| S | Gemma 3 4B | 4B | 2.8GB | 450 | 2.49 GB | 2.2M | 32.8k | gemma3 | |
| S | Phi-4 Mini 3.8B | 3.8B | 2.8GB | 474 | 2.49 GB | 1.5M | 131.1k | phi4 | |
| S | Nemotron Mini 4B | 4B | 3.0GB | 450 | 2.70 GB | 152.2k | 8.2k | nemotron | |
| S | Phi-3.5 Vision | 4.2B | 3.2GB | 429 | 2.50 GB | 1.8M | 131.1k | phi3v | |
| S | Stable Diffusion XL (CoreML) | 3.5B | 3.3GB | 514 | 3.05 GB | 2.1M | — | unet-diffusion | |
| S | Whisper Large v3 | 1.55B | 3.4GB | 1161 | 3.10 GB | 5M | — | whisper | |
| S | Yi 1.5 6B Chat | 6B | 3.9GB | 300 | 3.67 GB | 6.8k | 4.1k | yi | |
| S | DeepSeek Coder 6.7B | 6.7B | 4.3GB | 269 | 4.08 GB | 177.9k | 16.4k | llama | |
| S | Code Llama 7B | 7B | 4.3GB | 257 | 4.08 GB | 315.7k | 16.4k | llama | |
| S | OLMoE 1B-7B | 6.9B | 4.4GB | 1385 | 4.21 GB | 35.9k | 4.1k | olmoe | |
| S | Mistral 7B Instruct v0.3 | 7.3B | 4.6GB | 247 | 4.37 GB | 4.3M | 32.8k | mistral | |
| S | OpenChat 3.5 7B | 7B | 4.6GB | 257 | 4.37 GB | 37.6k | 8.2k | mistral | |
| S | StarCoder2 7B | 7B | 4.7GB | 257 | 4.46 GB | 12.4k | 16.4k | starcoder | |
| S | OLMo 2 7B | 7B | 4.7GB | 257 | 4.47 GB | 35.7k | 4.1k | olmo | |
| S | Qwen 2.5 Coder 7B | 7.6B | 4.9GB | 237 | 4.68 GB | 2.4M | 32.8k | qwen2 | |
| S | InternLM 2.5 7B | 7.7B | 4.9GB | 234 | 4.71 GB | 77.7k | 32.8k | internlm2 | |
| S | EXAONE 3.5 7.8B | 7.8B | 4.9GB | 231 | 4.77 GB | 192.4k | 32.8k | exaone | |
| S | LLaVA 1.6 7B | 7B | 5.0GB | 257 | 4.40 GB | 558.4k | 4.1k | llava | |
| S | Falcon 3 7B | 7B | 5.0GB | 257 | 4.40 GB | 14.7k | 8.2k | falcon | |
| S | SDXL Turbo (GGUF) | 3.5B | 5.0GB | 514 | 3.50 GB | 1M | — | unet-diffusion | |
| S | DeepSeek R1 Distill 8B | 8B | 5.1GB | 225 | 4.92 GB | 749.4k | 131.1k | llama | |
| S | Llama 3.1 8B Instruct | 8B | 5.1GB | 225 | 4.92 GB | 9.8M | 131.1k | llama | |
| S | Dolphin 3.0 Llama 3.1 8B | 8B | 5.1GB | 225 | 4.92 GB | 10.1k | 131.1k | llama | |
| S | NeuralDaredevil 8B (abliterated) | 8B | 5.1GB | 225 | 4.92 GB | 15.9k | 8.2k | llama | |
| S | Llama 3.1 8B Instruct (abliterated) | 8B | 5.1GB | 225 | 4.92 GB | 10.2k | 131.1k | llama | |
| S | Stheno L3 8B v3.2 | 8B | 5.1GB | 225 | 4.92 GB | 8.2k | 8.2k | llama | |
| S | Granite 3.3 8B | 8B | 5.1GB | 225 | 4.94 GB | 75.2k | 8.2k | granite | |
| S | Qwen 2.5 7B Instruct | 7.6B | 5.3GB | 237 | 4.70 GB | 12.4M | 131.1k | qwen2 | |
| S | Qwen3 8B Base | 8B | 5.3GB | 225 | 4.80 GB | 416.6k | 32.8k | qwen3 | |
| S | CodeGemma 7B | 8.5B | 5.5GB | 212 | 5.33 GB | 9.6k | 8.2k | gemma | |
| S | Yi 1.5 9B Chat | 9B | 5.5GB | 200 | 5.33 GB | 21.7k | 4.1k | yi | |
| S | Yi Coder 9B | 9B | 5.5GB | 200 | 5.33 GB | 10.5k | 4.1k | yi | |
| S | Gemma 2 9B Instruct | 9.2B | 5.9GB | 196 | 5.76 GB | 422.1k | 8.2k | gemma2 | |
| S | Stable Audio Open | 1B | 6.0GB | 1800 | 2.50 GB | 21.4k | — | stable-audio | |
| S | Falcon 3 10B | 10B | 6.4GB | 180 | 6.29 GB | 9.2k | 8.2k | falcon | |
| S | Solar 10.7B | 10.7B | 6.5GB | 168 | 6.46 GB | 62.7k | 4.1k | llama | |
| S | Gemma 3 MoE 9B | 9B | 7.0GB | 720 | 5.50 GB | — | 8.2k | gemma3-moe | |
| S | Gemma 3 12B | 12B | 7.3GB | 150 | 7.30 GB | 2.8M | 32.8k | gemma3 | |
| S | Mistral Nemo 12B | 12B | 7.5GB | 150 | 7.48 GB | 647.8k | 131.1k | mistral | |
| S | Magnum v4 12B | 12B | 7.5GB | 150 | 7.48 GB | 368 | 131.1k | mistral | |
| S | Rocinante 12B v1.1 | 12B | 7.5GB | 150 | 7.48 GB | 147 | 131.1k | mistral | |
| S | Mistral Nemo Base 12B | 12B | 7.7GB | 150 | 7.20 GB | 54.2k | 131.1k | mistral | |
| S | Code Llama 13B Instruct | 13B | 7.8GB | 138 | 7.87 GB | 4.7k | 16.4k | llama | |
| S | ACE-Step 1.5XL | 1.5B | 8.0GB | 1200 | 3.00 GB | — | — | acestep | |
| S | Qwen 2.5 14B | 14B | 8.9GB | 129 | 8.99 GB | 2.5M | 131.1k | qwen2 | |
| S | Qwen 2.5 Coder 14B | 14B | 8.9GB | 129 | 8.99 GB | 1.3M | 32.8k | qwen2 | |
| S | Phi-4 | 14B | 8.9GB | 129 | 9.05 GB | 786.3k | 16.4k | phi3 | |
| S | Stable Diffusion 3 Medium (GGUF) | 2.5B | 9.2GB | 720 | 9.29 GB | 5.8k | — | mmdit-diffusion | |
| S | Rocinante XL 16B v1 | 16B | 9.6GB | 112 | 9.75 GB | 176 | 131.1k | mistral | |
| S | DeepSeek MoE 16B | 16.4B | 11.0GB | 643 | 9.50 GB | 35.2k | 4.1k | deepseek-moe | |
| S | TRELLIS Image Large | 1.2B | 12.0GB | 1500 | 2.40 GB | 2.4M | — | trellis | |
| A | Mistral Small 22B | 22B | 12.9GB | 82 | 13.34 GB | 8.8k | 32.8k | mistral | |
| A | Codestral 22B (abliterated) | 22B | 12.9GB | 82 | 13.34 GB | 8.2k | 32.8k | mistral | |
| A | Magnum v4 22B | 22B | 12.9GB | 82 | 13.34 GB | 163 | 32.8k | mistral | |
| A | Dolphin 3.0 R1 Mistral 24B | 24B | 13.8GB | 75 | 14.33 GB | 1.2k | 131.1k | mistral | |
| A | Cydonia 24B v4.3 | 24B | 13.8GB | 75 | 14.33 GB | 4.2k | 32.8k | mistral | |
| A | FLUX.1 Schnell (GGUF) | 12B | 14.0GB | 150 | 12.00 GB | 680.1k | — | rectified-flow | |
| A | FLUX.1 Dev (GGUF) | 12B | 14.0GB | 150 | 12.00 GB | 735.5k | — | rectified-flow | |
| A | Dolphin Mistral 24B (Venice Edition) | 24B | 14.9GB | 75 | 14.40 GB | 14.3k | 32.8k | mistral | |
| A | Gemma 3 27B | 27B | 15.9GB | 67 | 16.55 GB | 692.9k | 32.8k | gemma3 | |
| A | Wan 2.2 TI2V 5B | 5B | 16.0GB | 360 | 10.00 GB | 7.3k | — | wan-dit | |
| A | CogVideoX 5B | 5B | 16.0GB | 360 | 10.00 GB | 36.1k | — | cogvideox | |
| A | Hunyuan3D 2 | 2.5B | 16.0GB | 720 | 5.00 GB | 82.6k | — | hunyuan3d | |
| B | Skyfall 31B v4.2 | 31B | 18.2GB | 58 | 18.98 GB | 2.4k | 131.1k | mistral | |
| B | Qwen 2.5 32B | 32B | 19.0GB | 56 | 19.85 GB | 648.7k | 131.1k | qwen2 | |
| B | Qwen3 30B-A3B | 30.5B | 20.0GB | 545 | 18.00 GB | — | 32.8k | qwen3-moe | |
| C | Phi-3.5 MoE | 41.9B | 24.1GB | 272 | 25.35 GB | 125k | 131.1k | phimoe | |
| C | Mixtral 8x7B Instruct | 46.7B | 25.1GB | 134 | 26.44 GB | 648.1k | 32.8k | mixtral | |
| D | Mochi 1 Preview | 10B | 30.0GB | offload | 20.00 GB | 9.5k | — | asymdit | |
| F | Llama 3.1 70B Instruct | 70B | 40.1GB | offload | 42.52 GB | 756.8k | 131.1k | llama | |
| F | Euryale L3.3 70B v2.3 | 70B | 40.1GB | offload | 42.52 GB | 485 | 131.1k | llama | |
| F | Llama 3.1 70B (lorablated) | 70B | 40.1GB | offload | 42.52 GB | 192 | 131.1k | llama | |
| F | Magnum v4 72B | 72B | 44.7GB | offload | 47.42 GB | 14.9k | 131.1k | qwen2 | |
| F | HunyuanVideo 13B | 13B | 60.0GB | offload | 26.00 GB | 811 | — | hunyuan-dit | |
| F | Qwen3 235B-A22B | 235B | 144.0GB | offload | 140.00 GB | — | 32.8k | qwen3-moe | |
| F | Mixtral 8x22B Instruct | 141B | 88.0GB | offload | 85.00 GB | 26.5k | 65.5k | mixtral |