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 |
|---|---|---|---|---|---|---|
| 201 | Qwen2.5-Coder-7B | 7.6 B | 33 K | ✓ apache-2.0 | 357 K | from 18.4 GB |
| 202 | phi-4 | 14.7 B | 16 K | ✓ mit | 356 K | from 34.9 GB |
| 203 | DeepSeek-V4-Pro | 1,598.8 B | 1.0 M | ✓ mit | 355 K | from 1,191.5 GB |
| 204 | RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata | — | — | ✓ apache-2.0 | 352 K | from 98.3 GB |
| 205 | Qwen3.5-122B-A10B-NVFP4 | 64.6 B | — | ✓ apache-2.0 | 351 K | from 102.0 GB |
| 206 | Kimi-K2-Instruct | 1,026.5 B | 131 K | other | 350 K | from 1,286.6 GB |
| 207 | CodeLlama-7b-hf | 6.7 B | 16 K | ⚠ llama2 | 347 K | from 16.3 GB |
| 208 | Phi-4-mini-instruct | 3.8 B | 131 K | ✓ mit | 347 K | from 9.5 GB |
| 209 | DeepSeek-R1-Distill-Qwen-32B | 32.8 B | 131 K | ✓ mit | 347 K | from 77.5 GB |
| 210 | LFM2.5-230M-GGUF | 230 M | — | other | 344 K | from 0.7 GB |
| 211 | gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF | — | — | ✓ apache-2.0 | 344 K | from 1.4 GB |
| 212 | Ornith-1.5-397B-FP8 | 403.4 B | — | ✓ mit | 343 K | from 521.2 GB |
| 213 | bloom-560m | 560 M | — | ⚠ bigscience-bloom-rail-1.0 | 342 K | from 1.8 GB |
| 214 | Qwen2.5-1.5B-Instruct-GGUF | — | — | ✓ apache-2.0 | 341 K | from 1.3 GB |
| 215 | granite-3.3-2b-instruct | 2.5 B | 131 K | ✓ apache-2.0 | 340 K | from 6.5 GB |
| 216 | Ternary-Bonsai-8B-gguf | — | — | ✓ apache-2.0 | 339 K | from 2.9 GB |
| 217 | Phi-3-mini-4k-instruct | 3.8 B | 4 K | ✓ mit | 337 K | from 9.5 GB |
| 218 | LFM2.5-1.2B-Instruct-GGUF | 1.2 B | 128 K | other | 337 K | from 1.4 GB |
| 219 | MiniCPM5-1B | 1.1 B | 131 K | ✓ apache-2.0 | 336 K | from 3.0 GB |
| 220 | gemma-2-9b-it-AWQ-INT4 | 9.2 B | 8 K | ⚠ gemma | 334 K | from 8.7 GB |
| 221 | Ornith-1.0-9B-GGUF | — | — | ✓ mit | 334 K | from 5.3 GB |
| 222 | GLM-5.2 | 753.3 B | 1.0 M | ✓ mit | 333 K | from 1,770.8 GB |
| 223 | Qwen2.5-Coder-14B-Instruct-AWQ | 14.8 B | 33 K | ✓ apache-2.0 | 332 K | from 13.7 GB |
| 224 | Qwen3.8-27B-DFlash2-GGUF | — | — | ✓ apache-2.0 | 329 K | from 1.8 GB |
| 225 | Ornith-1.5-35B-A3B-MLX | 34.7 B | — | unknown | 326 K | from 82.0 GB |
| 226 | Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF | — | — | ✓ mit | 324 K | from 12.5 GB |
| 227 | OTel-2.0-Decision-26B-A4B-4bit | 25.8 B | — | ✓ apache-2.0 | 323 K | from 23.3 GB |
| 228 | Qwen3-32B-NVFP4 | 32.0 B | 41 K | ✓ apache-2.0 | 322 K | from 28.0 GB |
| 229 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 318 K | from 3.7 GB |
| 230 | Qwen3.6-14B-A3B-FableVibes-GGUF | — | — | ✓ apache-2.0 | 318 K | from 6.4 GB |
| 231 | DeepSeek-V3.1 | 684.5 B | 164 K | ✓ mit | 316 K | from 860.6 GB |
| 232 | Ornith-1.5-9B-OBLITERATED | 9.7 B | — | ✓ mit | 312 K | from 6.3 GB |
| 233 | Mistral-7B-v0.1 | 7.2 B | 33 K | ✓ apache-2.0 | 311 K | from 17.5 GB |
| 234 | Qwen2.5-0.5B-Instruct-GGUF | — | — | ✓ apache-2.0 | 309 K | from 1.0 GB |
| 235 | Bonsai-27B-gguf | — | — | ✓ apache-2.0 | 308 K | from 1.2 GB |
| 236 | DeepSeek-R1-Distill-Qwen-14B | 14.8 B | 131 K | ✓ mit | 306 K | from 35.2 GB |
| 237 | DeepSeek-R1-Distill-Qwen-7B | 7.6 B | 131 K | ✓ mit | 306 K | from 18.4 GB |
| 238 | Olmo-3-7B-Instruct | 7.3 B | 66 K | ✓ apache-2.0 | 304 K | from 17.7 GB |
| 239 | Qwen3.6-27B-AWQ-4bit | 27.7 B | — | ✓ apache-2.0 | 302 K | from 25.2 GB |
| 240 | Llama-3.2-3B-Instruct | 3.2 B | 131 K | ⚠ llama3.2 | 300 K | from 8.0 GB |
| 241 | Qwen3-0.6B-GGUF | 600 M | 41 K | ✓ apache-2.0 | 300 K | from 1.3 GB |
| 242 | Ornith-1.5-9B-MLX-8bit | 9.0 B | — | unknown | 297 K | from 12.3 GB |
| 243 | Ornith-1.5-9B-MLX | 9.0 B | — | unknown | 297 K | from 21.5 GB |
| 244 | Jan-v3.5-4B-gguf | — | — | ✓ apache-2.0 | 293 K | from 2.8 GB |
| 245 | JiRackUltra_14b | 14.8 B | 131 K | ✓ mit | 292 K | from 9.1 GB |
| 246 | zeta-2.1-autoround-W4A16 | 2.2 B | 33 K | unknown | 292 K | from 7.6 GB |
| 247 | Qwen2.5-7B-Instruct-GPTQ-Int4 | 7.6 B | 33 K | ✓ apache-2.0 | 291 K | from 7.8 GB |
| 248 | Qwen2.5-Coder-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 290 K | from 3.8 GB |
| 249 | xflux_text_encoders | 4.8 B | — | ✓ apache-2.0 | 281 K | from 11.7 GB |
| 250 | llm-jp-4-33b-thinking-gguf | 33.0 B | — | ✓ apache-2.0 | 271 K | from 27.6 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.