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 |
|---|---|---|---|---|---|---|
| 251 | Qwen-AgentWorld-35B-A3B-GGUF | — | — | ✓ apache-2.0 | 270 K | from 13.1 GB |
| 252 | GLM-5.3-Flash-Maya-GGUF | 321.3 B | — | ✓ mit | 267 K | from 49.9 GB |
| 253 | taardis-27b-full-ternary | 27.0 B | — | ✓ apache-2.0 | 267 K | from 12.4 GB |
| 254 | Qwen3-8B-64k-Context-2X-Josiefied-Uncensored | 8.2 B | 66 K | unknown | 265 K | from 19.7 GB |
| 255 | Qwen3-30B-A3B-GGUF | — | — | ✓ apache-2.0 | 265 K | from 20.9 GB |
| 256 | Qwopus3.6-27B-Fusion-GGUF | — | — | other | 265 K | from 15.4 GB |
| 257 | Step-3.5-Flash | 199.4 B | 262 K | ✓ apache-2.0 | 264 K | from 469.1 GB |
| 258 | Ornith-1.0-397B-FP8 | 396.8 B | — | ✓ mit | 262 K | from 505.7 GB |
| 259 | Ornith-1.5-35B-A3B | 36.0 B | — | ✓ mit | 260 K | from 85.0 GB |
| 260 | Qwen3.8-4B-Distill | 4.7 B | — | ✓ apache-2.0 | 258 K | from 11.5 GB |
| 261 | gemma-2-2b-it | 2.6 B | — | ⚠ gemma | 258 K | from 6.6 GB |
| 262 | droplychee-1.0-27b | 27.8 B | — | ✓ apache-2.0 | 252 K | from 65.8 GB |
| 263 | NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | 31.6 B | 262 K | other | 251 K | from 41.2 GB |
| 264 | Hy3-GGUF | — | — | ✓ apache-2.0 | 248 K | from 52.9 GB |
| 265 | Qwen2-0.5B-Instruct | 490 M | 33 K | ✓ apache-2.0 | 247 K | from 1.7 GB |
| 266 | Qwen3-14B-GGUF | — | — | ✓ apache-2.0 | 246 K | from 10.4 GB |
| 267 | Mistral-Small-3.1-24B-Instruct-2503 | 24.0 B | — | ✓ apache-2.0 | 246 K | from 109.8 GB |
| 268 | Qwen2.5-Coder-7B-Instruct-4bit | 1.2 B | 33 K | ✓ apache-2.0 | 246 K | from 5.4 GB |
| 269 | Qwen_Qwen3-4B-GGUF | 4.0 B | 41 K | unknown | 245 K | from 2.8 GB |
| 270 | DeepSeek-V4-Flash-GGUF | — | — | ✓ mit | 245 K | from 44.1 GB |
| 271 | OTel-LLM-8B-A1B-IT | — | 128 K | ✓ apache-2.0 | 245 K | — |
| 272 | Kwaipilot_KAT-Coder-V2.5-Dev-GGUF | — | — | ✓ apache-2.0 | 244 K | from 11.3 GB |
| 273 | Ornith-1.5-9B-MLX-4bit | 9.0 B | — | unknown | 243 K | from 7.4 GB |
| 274 | gpt-neox-20b | 20.7 B | 2 K | ✓ apache-2.0 | 243 K | from 49.0 GB |
| 275 | SmolLM2-1.7B-Instruct | 1.7 B | 8 K | ✓ apache-2.0 | 242 K | from 4.5 GB |
| 276 | Ling-3.0-tiny-GGUF | — | 131 K | ✓ mit | 242 K | from 2.4 GB |
| 277 | h2ovl-mississippi-800m | 830 M | — | ✓ apache-2.0 | 242 K | from 2.4 GB |
| 278 | Qwen3-30B-A3B-Instruct-2507-FP8 | 30.5 B | 262 K | ✓ apache-2.0 | 242 K | from 39.4 GB |
| 279 | Qwen3.8-27B-DSpark | 1.9 B | 262 K | other | 241 K | from 4.9 GB |
| 280 | s1-mini-GGUF | — | — | other | 241 K | from 1.0 GB |
| 281 | Qwen3-8B-FP8 | 8.2 B | 41 K | ✓ apache-2.0 | 240 K | from 12.1 GB |
| 282 | Vikhr-Nemo-12B-Instruct-R-21-09-24 | 12.3 B | 1.0 M | ✓ apache-2.0 | 239 K | from 30.8 GB |
| 283 | TwIL-LM3 | 3.1 B | 66 K | other | 239 K | from 3.1 GB |
| 284 | gemma-3-270m | 270 M | — | ⚠ gemma | 238 K | from 1.1 GB |
| 285 | Qwen2-1.5B-Instruct | 1.5 B | 33 K | ✓ apache-2.0 | 237 K | from 4.1 GB |
| 286 | Phi-3-mini-128k-instruct | 3.8 B | 131 K | ✓ mit | 237 K | from 9.5 GB |
| 287 | EXAONE-3.5-7.8B-Instruct | 7.8 B | 33 K | other | 236 K | from 36.1 GB |
| 288 | gemma4-e4b-claims-comparison | 7.9 B | — | ⚠ gemma | 233 K | from 19.2 GB |
| 289 | Qwen2.5-72B-Instruct | 72.7 B | 33 K | other | 232 K | from 171.4 GB |
| 290 | diffusiongemma-26B-A4B-it-NVFP4 | 14.4 B | — | ✓ apache-2.0 | 232 K | from 23.4 GB |
| 291 | h2ovl-mississippi-2b | 2.2 B | — | ✓ apache-2.0 | 230 K | from 5.6 GB |
| 292 | POCKET-26B-GGUF | 26.0 B | — | ✓ apache-2.0 | 230 K | from 16.6 GB |
| 293 | Llama-3.1-8B-Instruct-4bit | 1.3 B | 131 K | ⚠ llama3.1 | 228 K | from 5.7 GB |
| 294 | Kimi-K2.5-NVFP4 | — | — | other | 228 K | from 650.4 GB |
| 295 | GLM-4.7-Flash-GGUF | — | — | ✓ mit | 228 K | from 13.0 GB |
| 296 | Qwen2.5-Math-1.5B | 1.5 B | 4 K | ✓ apache-2.0 | 228 K | from 4.1 GB |
| 297 | llama-3-8b-Instruct-bnb-4bit | 8.2 B | 8 K | ⚠ llama3 | 227 K | from 8.0 GB |
| 298 | Kimi-K2-Thinking-NVFP4 | 519.1 B | 262 K | other | 227 K | from 732.0 GB |
| 299 | Spark-X2.5-1.7B-GGUF | 1.7 B | — | ✓ apache-2.0 | 225 K | from 2.0 GB |
| 300 | Qwen2-7B | 7.6 B | 131 K | ✓ apache-2.0 | 225 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.