1,226 models · 1,226 open weights · 200 API-only · refreshed nightly
Open-weights models
Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 301 | Llama-3.2-3B | 3.2 B | — | ⚠ llama3.2 | 225 K | from 8.0 GB |
| 302 | Qwen3-14B-Base | 14.8 B | 33 K | ✓ apache-2.0 | 224 K | from 35.2 GB |
| 303 | Qwen3.6-35B-A3B-NVFP4-MTP-GGUF | — | — | unknown | 223 K | from 23.0 GB |
| 304 | Ornith-1.5-397B | 403.4 B | — | ✓ mit | 222 K | from 948.5 GB |
| 305 | MiniMax-M2.5-NVFP4 | 116.4 B | 197 K | other | 222 K | from 171.8 GB |
| 306 | POCKET-Darwin-180B-GGUF | 180.0 B | — | other | 222 K | from 82.3 GB |
| 307 | Qwen3-235B-A22B-Instruct-2507-FP8 | 235.1 B | 262 K | ✓ apache-2.0 | 222 K | from 295.8 GB |
| 308 | gpt-oss-20b-GGUF | 20.0 B | 131 K | ✓ apache-2.0 | 222 K | from 4.5 GB |
| 309 | LLaDA-8B-Instruct | 8.0 B | — | ✓ mit | 221 K | from 19.3 GB |
| 310 | GLM-4.7-Flash-AWQ-4bit | 32.1 B | 203 K | ✓ mit | 221 K | from 27.5 GB |
| 311 | Qwen3-1.7B-GGUF | 1.7 B | 41 K | ✓ apache-2.0 | 220 K | from 1.6 GB |
| 312 | Olmo-3-7B-Instruct-SFT | 7.3 B | 66 K | ✓ apache-2.0 | 220 K | from 17.7 GB |
| 313 | Ling-3.0-flash-GGUF | 127.5 B | 262 K | ✓ mit | 220 K | from 55.2 GB |
| 314 | Ornith-1.0-35B-FP8 | 35.1 B | — | ✓ mit | 220 K | from 47.2 GB |
| 315 | Agents-A1-4B-Q8_0-GGUF | — | — | ✓ apache-2.0 | 219 K | from 1.2 GB |
| 316 | automotive | 34.7 B | — | ✓ apache-2.0 | 219 K | from 29.0 GB |
| 317 | Llama-3.1-Nemotron-Nano-8B-v1 | 8.0 B | 131 K | other | 218 K | from 19.4 GB |
| 318 | Qwen2-0.5B | 490 M | 131 K | ✓ apache-2.0 | 218 K | from 1.7 GB |
| 319 | NVIDIA-Nemotron-Nano-9B-v2 | 8.9 B | 131 K | other | 217 K | from 21.4 GB |
| 320 | sarvam-30b | 32.2 B | 131 K | ✓ apache-2.0 | 217 K | from 146.8 GB |
| 321 | Gemma-4-E4B-DECKARD-HERETIC-NVFP4 | 6.2 B | — | ⚠ gemma | 216 K | from 12.6 GB |
| 322 | TinyLLama-v0 | <0.1 M | 2 K | ✓ apache-2.0 | 215 K | from 0.5 GB |
| 323 | Parable-Qwen3-8B-Claude-Fable-5-GGUF | 8.0 B | 41 K | ✓ apache-2.0 | 215 K | from 7.2 GB |
| 324 | qwen3-4b-base-dapo-v4 | 4.0 B | 33 K | ✓ apache-2.0 | 215 K | from 10.0 GB |
| 325 | Qwen2.5-Coder-1.5B-Instruct-GGUF | 1.5 B | 33 K | ✓ apache-2.0 | 215 K | from 1.6 GB |
| 326 | MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF | — | — | ✓ apache-2.0 | 215 K | from 1.8 GB |
| 327 | Qwen3Guard-Gen-0.6B | 750 M | 33 K | ✓ apache-2.0 | 214 K | from 2.3 GB |
| 328 | vlt5-base-keywords | 280 M | — | ✓ cc-by-4.0 | 214 K | from 1.8 GB |
| 329 | SmolLM3-3B-Base | 3.1 B | 66 K | ✓ apache-2.0 | 213 K | from 7.7 GB |
| 330 | OTel-2.0-LLM-31B-IT | 31.3 B | 262 K | ✓ apache-2.0 | 212 K | from 144.6 GB |
| 331 | OTel-LLM-27B-IT | 27.0 B | — | ✓ apache-2.0 | 212 K | from 64.0 GB |
| 332 | GLM-5.2-NVFP4 | 381.0 B | 1.0 M | ✓ mit | 212 K | from 569.0 GB |
| 333 | wildguard | 7.3 B | — | ✓ apache-2.0 | 211 K | from 17.5 GB |
| 334 | Qwen2.5-3B-Instruct-GGUF | — | — | other | 211 K | from 2.0 GB |
| 335 | Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 | 35.1 B | — | ✓ mit | 211 K | from 83.0 GB |
| 336 | MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF | — | — | ✓ apache-2.0 | 211 K | from 1.3 GB |
| 337 | Parable-Qwen3-4B-Claude-Fable-5-GGUF | 4.0 B | 41 K | ✓ apache-2.0 | 210 K | from 3.8 GB |
| 338 | Qwen3-1.7B | 2.0 B | 41 K | ✓ apache-2.0 | 210 K | from 5.3 GB |
| 339 | Llama-3.3-70B-Instruct | 70.6 B | — | ⚠ llama3.3 | 210 K | from 166.3 GB |
| 340 | Qwen3-30B-A3B-GPTQ-Int4 | 30.5 B | 41 K | ✓ apache-2.0 | 208 K | from 23.7 GB |
| 341 | DeepSeek-R1-Distill-Llama-70B-GGUF | — | 131 K | ⚠ llama3.3 | 208 K | from 29.5 GB |
| 342 | Bielik-11B-v3.0-Instruct-awq | 11.3 B | 33 K | ✓ apache-2.0 | 208 K | from 9.0 GB |
| 343 | Qwen3.6-35B-A3B-DFlash | 390 M | 262 K | ✓ apache-2.0 | 208 K | from 1.4 GB |
| 344 | Mistral-7B-Instruct-v0.3-AWQ | 7.3 B | 33 K | ✓ apache-2.0 | 208 K | from 6.2 GB |
| 345 | The_GuageLLM_23M | 20 M | — | ✓ apache-2.0 | 207 K | from 0.6 GB |
| 346 | Qwen3Guard-Gen-4B | 4.4 B | 33 K | ✓ apache-2.0 | 207 K | from 10.9 GB |
| 347 | Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata | 180.0 B | — | other | 207 K | from 83.8 GB |
| 348 | Mistral-7B-Instruct-v0.2-AWQ | 7.2 B | 33 K | ✓ apache-2.0 | 205 K | from 6.2 GB |
| 349 | Qwen2.5-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 205 K | from 3.6 GB |
| 350 | Nemotron-Labs-Diffusion-8B | 8.5 B | 262 K | other | 204 K | from 20.6 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.