1,213 models · 1,213 open weights · 210 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 | On RTX 3060 · 12 GB |
|---|---|---|---|---|---|---|
| 301 | Llama-3.2-1B | 1.2 B | — | ⚠ llama3.2 | 477 K | 3.4 GB |
| 302 | embeddinggemma-2 | 744 M | — | ✓ apache-2.0 | 475 K | 2.2 GB |
| 303 | sentence-bert-base-ja-mean-tokens-v2 | 110 M | 512 | cc-by-sa-4.0 | 474 K | 1.0 GB |
| 304 | llama-3-8b-Instruct-bnb-4bit | 8.2 B | 8 K | ⚠ llama3 | 472 K | 8.0 GB |
| 305 | wav2vec2-large-xlsr-japanese-hiragana | 320 M | — | ✓ apache-2.0 | 472 K | 1.9 GB |
| 306 | nli-mpnet-base-v2 | 110 M | 512 | ✓ apache-2.0 | 472 K | 1.0 GB |
| 307 | bge-small-en-v1.5 | 33 M | 512 | ✓ mit | 470 K | 0.7 GB |
| 308 | wav2vec2-large-xlsr-kazakh | 320 M | — | ✓ apache-2.0 | 466 K | 1.9 GB |
| 309 | pplx-embed-v1-0.6b | 600 M | 33 K | ✓ mit | 461 K | 3.2 GB |
| 310 | rubert-tiny2 | 30 M | 2 K | ✓ mit | 460 K | 0.6 GB |
| 311 | nsfw_image_detector | 90 M | — | ✓ mit | 460 K | 0.7 GB |
| 312 | sat-3l-sm | 210 M | 514 | ✓ mit | 460 K | 1.5 GB |
| 313 | robertuito-sentiment-analysis | 110 M | 128 | unknown | 459 K | 1.0 GB |
| 314 | gpt-neo-125m | 150 M | 2 K | ✓ mit | 458 K | 1.1 GB |
| 315 | mimi | 100 M | 8 K | ✓ cc-by-4.0 | 458 K | 0.9 GB |
| 316 | multilingual-e5-small | 120 M | 512 | unknown | 456 K | 0.8 GB |
| 317 | MedCPT-Query-Encoder | 110 M | 512 | other | 454 K | 1.0 GB |
| 318 | open-vakgyata | 60 M | — | ✗ cc-by-nc-4.0 | 453 K | 0.8 GB |
| 319 | gte-base-en-v1.5 | 137 M | 8 K | ✓ apache-2.0 | 452 K | 1.1 GB |
| 320 | Qwen3-4B-Base | 4.0 B | 33 K | ✓ apache-2.0 | 447 K | 10.0 GB |
| 321 | Mellum2.1-12B-A2.5B-Thinking-GGUF | 12.0 B | — | ✓ apache-2.0 | 446 K | 11.5 GB |
| 322 | MiniCPM5-2B-GGUF | 2.0 B | — | ✓ apache-2.0 | 446 K | 2.5 GB |
| 323 | Qwen2.5-Coder-3B-Instruct | 3.1 B | 33 K | other | 441 K | 7.8 GB |
| 324 | sqlcoder-7b-2 | 6.7 B | 16 K | cc-by-sa-4.0 | 441 K | 6.8 GB |
| 325 | nllb-200-distilled-1.3B | 1.3 B | 1 K | ✗ cc-by-nc-4.0 | 440 K | 3.6 GB |
| 326 | Qwen2.5-0.5B-Instruct-GGUF | — | — | ✓ apache-2.0 | 440 K | 1.0 GB |
| 327 | Apodex-1.1-mini-GGUF | — | — | ✓ apache-2.0 | 439 K | 10.2 GB |
| 328 | S-PubMedBert-MedQuAD | 110 M | 512 | ✓ mit | 439 K | 1.0 GB |
| 329 | Qwen3.8-27B-DFlash2 | 1.9 B | 262 K | ✓ apache-2.0 | 438 K | 5.0 GB |
| 330 | clipseg-rd64-refined | 150 M | — | ✓ apache-2.0 | 437 K | 1.2 GB |
| 331 | Qwen-Image-2.1-Lightning | 7.1 B | — | unknown | 436 K | 1.6 GB |
| 332 | segformer_b2_clothes | 30 M | — | other | 434 K | 0.6 GB |
| 333 | vram-16 | — | — | unknown | 432 K | 0.5 GB |
| 334 | lambda | — | — | unknown | 428 K | 0.5 GB |
| 335 | efficient-splade-VI-BT-large-doc | — | 512 | ✗ cc-by-nc-sa-4.0 | 427 K | 0.5 GB |
| 336 | Qwen3-14B-GGUF | — | — | ✓ apache-2.0 | 424 K | 10.4 GB |
| 337 | maple-preview-GGUF | — | — | ✓ mit | 424 K | 6.5 GB |
| 338 | Ling-3.0-tiny-MLX-4bit | 7.9 B | 131 K | ✓ mit | 420 K | 6.6 GB |
| 339 | german-sentiment-bert | 109 M | 512 | ✓ mit | 419 K | 1.0 GB |
| 340 | Ornith-1.0-9B-GGUF | — | — | ✓ mit | 418 K | 5.3 GB |
| 341 | llama2-embedding-1b-8k | 947 M | 33 K | unknown | 416 K | 4.8 GB |
| 342 | RMBG-2.0 | 221 M | — | other | 408 K | 1.5 GB |
| 343 | locate-anything.cpp-gguf | 3.8 B | — | other | 405 K | 6.3 GB |
| 344 | vit_base_patch16_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 402 K | 0.9 GB |
| 345 | Qwen2.5-Coder-1.5B-Instruct | 1.5 B | 33 K | ✓ apache-2.0 | 402 K | 4.1 GB |
| 346 | BioLORD-2023 | 110 M | 512 | other | 399 K | 1.0 GB |
| 347 | LLM2Vec-Meta-Llama-3-8B-Instruct-mntp | 8.0 B | 8 K | ✓ mit | 396 K | 1.9 GB |
| 348 | mistral-7b-v0.3-bnb-4bit | 7.5 B | 33 K | ✓ apache-2.0 | 392 K | 6.2 GB |
| 349 | Qwen2.5-Coder-1.5B | 1.5 B | 33 K | ✓ apache-2.0 | 387 K | 4.1 GB |
| 350 | SmolLM3-3B | 3.1 B | 66 K | ✓ apache-2.0 | 386 K | 7.7 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.