1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Text generation models
Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 151 | Sage-A1.5-Q8_0-GGUF | — | — | ✓ apache-2.0 | 490 K | from 1.5 GB |
| 152 | Qwen2.5-32B-Instruct-GPTQ-Int4 | 32.8 B | 33 K | ✓ apache-2.0 | 487 K | from 26.7 GB |
| 153 | Qwen3-Coder-30B-A3B-Instruct-GGUF | — | — | ✓ apache-2.0 | 486 K | from 12.9 GB |
| 154 | POCKET-Darwin-180B-GGUF | 180.0 B | — | other | 484 K | from 82.3 GB |
| 155 | Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 | 7.6 B | 33 K | ✓ apache-2.0 | 482 K | from 7.8 GB |
| 156 | Qwen3.8-27B-DFlash2-GGUF | — | — | ✓ apache-2.0 | 481 K | from 1.8 GB |
| 157 | NVIDIA-Nemotron-3.5-Bolt-E4B-GGUF | 4.0 B | — | other | 481 K | from 5.0 GB |
| 158 | Ornith-1.5-397B-NVFP4 | 397.0 B | — | ✓ mit | 478 K | from 411.4 GB |
| 159 | Ornith-1.5-35B-A3B-FP8 | 36.0 B | — | ✓ mit | 478 K | from 49.2 GB |
| 160 | Llama-3.2-1B | 1.2 B | — | ⚠ llama3.2 | 477 K | from 3.4 GB |
| 161 | Llama-3.1-8B | 8.0 B | — | ⚠ llama3.1 | 475 K | from 19.4 GB |
| 162 | llama-3-8b-Instruct-bnb-4bit | 8.2 B | 8 K | ⚠ llama3 | 472 K | from 8.0 GB |
| 163 | Qwen2.5-7B | 7.6 B | 131 K | ✓ apache-2.0 | 469 K | from 18.4 GB |
| 164 | JiRackDeltaNet_27b | 27.3 B | 262 K | ✓ mit | 468 K | from 16.5 GB |
| 165 | Qwen3.8-Flash-Next-GGUF | 180.0 B | — | other | 467 K | from 28.5 GB |
| 166 | Llama-3.1-405B-FP8 | 405.9 B | — | ⚠ llama3.1 | 465 K | from 597.3 GB |
| 167 | gpt-neo-125m | 150 M | 2 K | ✓ mit | 458 K | from 1.1 GB |
| 168 | Qwen3.6-27B-AWQ-4bit | 27.7 B | — | ✓ apache-2.0 | 454 K | from 25.2 GB |
| 169 | Qwen3-4B-Base | 4.0 B | 33 K | ✓ apache-2.0 | 447 K | from 10.0 GB |
| 170 | Mellum2.1-12B-A2.5B-Thinking-GGUF | 12.0 B | — | ✓ apache-2.0 | 446 K | from 11.5 GB |
| 171 | MiniCPM5-2B-GGUF | 2.0 B | — | ✓ apache-2.0 | 446 K | from 2.5 GB |
| 172 | NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | 67.2 B | 262 K | other | 445 K | from 98.9 GB |
| 173 | Qwen2.5-Coder-3B-Instruct | 3.1 B | 33 K | other | 441 K | from 7.8 GB |
| 174 | sqlcoder-7b-2 | 6.7 B | 16 K | cc-by-sa-4.0 | 441 K | from 6.8 GB |
| 175 | Qwen2.5-0.5B-Instruct-GGUF | — | — | ✓ apache-2.0 | 440 K | from 1.0 GB |
| 176 | Apodex-1.1-mini-GGUF | — | — | ✓ apache-2.0 | 439 K | from 10.2 GB |
| 177 | Qwen3.8-27B-DFlash2 | 1.9 B | 262 K | ✓ apache-2.0 | 438 K | from 5.0 GB |
| 178 | LFM2.5-24B-A2B-GGUF | 24.0 B | 131 K | other | 430 K | from 12.3 GB |
| 179 | Qwen3-Coder-Next | 79.7 B | 262 K | ✓ apache-2.0 | 426 K | from 187.7 GB |
| 180 | Qwen3-14B-GGUF | — | — | ✓ apache-2.0 | 424 K | from 10.4 GB |
| 181 | maple-preview-GGUF | — | — | ✓ mit | 424 K | from 6.5 GB |
| 182 | Meta-Llama-3-8B-Instruct-abliterated-v3 | 8.0 B | 8 K | ⚠ llama3 | 420 K | from 19.4 GB |
| 183 | Ling-3.0-tiny-MLX-4bit | 7.9 B | 131 K | ✓ mit | 420 K | from 6.6 GB |
| 184 | Ornith-1.0-9B-GGUF | — | — | ✓ mit | 418 K | from 5.3 GB |
| 185 | saiga_llama3_8b | 8.0 B | 8 K | other | 415 K | from 19.4 GB |
| 186 | pythia-6.9b | 7.0 B | 2 K | ✓ apache-2.0 | 414 K | from 16.8 GB |
| 187 | Ornith-1.5-122B-FP8 | 125.1 B | — | ✓ mit | 413 K | from 165.5 GB |
| 188 | EXAONE-3.5-7.8B-Instruct | 7.8 B | 33 K | other | 411 K | from 36.1 GB |
| 189 | Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit | 30.0 B | 262 K | ✓ apache-2.0 | 406 K | from 24.9 GB |
| 190 | Mistral-7B-v0.1 | 7.2 B | 33 K | ✓ apache-2.0 | 405 K | from 17.5 GB |
| 191 | Qwen2.5-Coder-1.5B-Instruct | 1.5 B | 33 K | ✓ apache-2.0 | 402 K | from 4.1 GB |
| 192 | mistral-7b-v0.3-bnb-4bit | 7.5 B | 33 K | ✓ apache-2.0 | 392 K | from 6.2 GB |
| 193 | Qwen2.5-Coder-1.5B | 1.5 B | 33 K | ✓ apache-2.0 | 387 K | from 4.1 GB |
| 194 | Ornith-1.0-397B | 396.8 B | — | ✓ mit | 387 K | from 933.0 GB |
| 195 | SmolLM3-3B | 3.1 B | 66 K | ✓ apache-2.0 | 386 K | from 7.7 GB |
| 196 | Meta-Llama-3-8B-Instruct | 8.0 B | — | ⚠ llama3 | 386 K | from 19.4 GB |
| 197 | humanizer | 12.0 B | — | ✓ apache-2.0 | 380 K | from 6.6 GB |
| 198 | Qwen3-Coder-Next-FP8 | 79.7 B | 262 K | ✓ apache-2.0 | 378 K | from 100.9 GB |
| 199 | bloom-560m | 560 M | — | ⚠ bigscience-bloom-rail-1.0 | 378 K | from 1.8 GB |
| 200 | Qwen2.5-Coder-7B | 7.6 B | 33 K | ✓ apache-2.0 | 377 K | from 18.4 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.