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 |
|---|---|---|---|---|---|---|
| 401 | Ornith-1.5-35B-A3B-MLX-8bit | 34.7 B | — | unknown | 192 K | from 46.2 GB |
| 402 | Kimi-K2.5-NVFP4 | — | — | other | 192 K | from 650.4 GB |
| 403 | Qwen2.5-Coder-14B-Instruct-GGUF | 14.0 B | 33 K | ✓ apache-2.0 | 192 K | from 8.9 GB |
| 404 | Llama-3.2-3B-Instruct-GGUF | — | — | ⚠ llama3.2 | 191 K | from 2.3 GB |
| 405 | Qwen3.8-27B-DSpark | 1.9 B | 262 K | other | 190 K | from 4.9 GB |
| 406 | NVIDIA-Nemotron-Nano-9B-v2-FP8 | 8.9 B | 131 K | other | 190 K | from 13.1 GB |
| 407 | Qwen3-14B-unsloth-bnb-4bit | 15.2 B | 41 K | ✓ apache-2.0 | 190 K | from 15.0 GB |
| 408 | DeepSeek-R1-Distill-Qwen-14B | 14.8 B | 131 K | ✓ mit | 190 K | from 35.2 GB |
| 409 | DeepSeek-R1-0528-Qwen3-8B-MLX-8bit | 2.3 B | 131 K | ✓ mit | 189 K | from 10.4 GB |
| 410 | gemma-3-1b-it-GGUF | 1.0 B | — | ⚠ gemma | 187 K | from 1.5 GB |
| 411 | LFM2.5-2.6B-GGUF | 2.6 B | 131 K | other | 187 K | from 2.6 GB |
| 412 | Qwen3.6-14B-A3B-FableVibes-GGUF | — | — | ✓ apache-2.0 | 187 K | from 6.4 GB |
| 413 | Ornith-1.0-397B | 396.8 B | — | ✓ mit | 187 K | from 933.0 GB |
| 414 | opt-350m | 350 M | 2 K | other | 185 K | from 1.3 GB |
| 415 | Qwen_Qwen3-0.6B-GGUF | 600 M | 41 K | unknown | 185 K | from 1.0 GB |
| 416 | Ornith-1.5-35B-A3B-MLX-4bit | 34.7 B | — | unknown | 183 K | from 27.2 GB |
| 417 | Qwen3-30B-A3B-Instruct-2507-FP8 | 30.5 B | 262 K | ✓ apache-2.0 | 182 K | from 39.4 GB |
| 418 | phi-2 | 2.8 B | 2 K | ✓ mit | 178 K | from 7.0 GB |
| 419 | Ministral-3-14B-Instruct-2512 | 13.9 B | — | ✓ apache-2.0 | 177 K | from 37.2 GB |
| 420 | Qwen3-Coder-Next-GGUF | — | — | ✓ apache-2.0 | 177 K | from 47.4 GB |
| 421 | Qwen3-1.7B-GGUF | 1.7 B | 41 K | ✓ apache-2.0 | 176 K | from 2.8 GB |
| 422 | Qwen3.8-4B-Distill | 4.7 B | — | ✓ apache-2.0 | 175 K | from 11.5 GB |
| 423 | Ternary-Bonsai-8B-gguf | — | — | ✓ apache-2.0 | 174 K | from 2.9 GB |
| 424 | Underdog-Saluki-27B-1.0-MTP-GGUF | 27.0 B | — | ✓ apache-2.0 | 173 K | from 13.7 GB |
| 425 | t5gemma-2b-2b-ul2-it | 5.6 B | — | ⚠ gemma | 173 K | from 13.7 GB |
| 426 | deepseek-coder-7b-instruct-v1.5 | 6.9 B | 4 K | other | 172 K | from 16.7 GB |
| 427 | gpt-oss-20b-MXFP4-Q8 | 20.9 B | 131 K | ✓ apache-2.0 | 171 K | from 16.9 GB |
| 428 | Meta-Llama-3.1-8B-Instruct | 8.0 B | 131 K | ⚠ llama3.1 | 169 K | from 19.4 GB |
| 429 | Qwen-AgentWorld-35B-A3B-GGUF | — | — | ✓ apache-2.0 | 169 K | from 13.1 GB |
| 430 | MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF | — | — | ✓ apache-2.0 | 168 K | from 1.8 GB |
| 431 | Qwen2.5-72B-Instruct | 72.7 B | 33 K | other | 167 K | from 171.4 GB |
| 432 | gpt2-medium | 380 M | — | ✓ mit | 166 K | from 2.2 GB |
| 433 | Qwen3-0.6B-GGUF | 600 M | 41 K | ✓ apache-2.0 | 165 K | from 0.9 GB |
| 434 | Qwen2-0.5B | 490 M | 131 K | ✓ apache-2.0 | 165 K | from 1.7 GB |
| 435 | LFM2.5-350M-GGUF | 350 M | 128 K | other | 165 K | from 0.8 GB |
| 436 | DeepSeek-R1-0528 | 684.5 B | 164 K | ✓ mit | 164 K | from 860.6 GB |
| 437 | Parable-Granite-4.1-3B-Claude-Fable-5-GGUF | 3.0 B | 131 K | ✓ apache-2.0 | 163 K | from 3.3 GB |
| 438 | Qwen3-VL-30B-A3B-Instruct-AWQ | 31.1 B | — | ✓ apache-2.0 | 163 K | from 24.8 GB |
| 439 | Parable-Granite-4.1-8B-Claude-Fable-5-GGUF | 8.0 B | 131 K | ✓ apache-2.0 | 162 K | from 7.3 GB |
| 440 | Qwen3-8B-GGUF | — | 41 K | ✓ apache-2.0 | 162 K | from 4.1 GB |
| 441 | Qwen1.5-1.8B-Chat | 1.8 B | 33 K | other | 161 K | from 4.8 GB |
| 442 | LFM2.5-350M | 355 M | 128 K | other | 161 K | from 1.3 GB |
| 443 | DeepSeek-R1-0528-Qwen3-8B-GGUF | 8.0 B | 131 K | ✓ mit | 161 K | from 5.3 GB |
| 444 | Ornith-1.5-35B-A3B-MLX-6bit | 34.7 B | — | unknown | 161 K | from 36.7 GB |
| 445 | Mistral-Small-3.1-24B-Instruct-2503 | 24.0 B | — | ✓ apache-2.0 | 159 K | from 109.8 GB |
| 446 | Qwen2-7B | 7.6 B | 131 K | ✓ apache-2.0 | 157 K | from 18.4 GB |
| 447 | Bonsai-1.7B-gguf | 1.7 B | — | ✓ apache-2.0 | 157 K | from 1.0 GB |
| 448 | Kimi-K2.6-NVFP4 | — | — | other | 157 K | from 655.2 GB |
| 449 | Qwen3-Coder-30B-A3B-Instruct-AWQ | 30.0 B | 262 K | ✓ apache-2.0 | 155 K | from 23.4 GB |
| 450 | Qwen2.5-14B-Instruct-1M | 14.8 B | 1.0 M | ✓ apache-2.0 | 154 K | from 35.2 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.