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 |
|---|---|---|---|---|---|---|
| 351 | humanizer | 12.0 B | — | ✓ apache-2.0 | 380 K | 6.6 GB |
| 352 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 379 K | 3.1 GB |
| 353 | bloom-560m | 560 M | — | ⚠ bigscience-bloom-rail-1.0 | 378 K | 1.8 GB |
| 354 | Qwen2.5-Coder-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 376 K | 3.8 GB |
| 355 | audiobox-aesthetics | 100 M | — | ✓ cc-by-4.0 | 375 K | 1.0 GB |
| 356 | deid_roberta_i2b2 | 350 M | 512 | ✓ mit | 369 K | 2.1 GB |
| 357 | Phi-3.5-mini-instruct | 3.8 B | 131 K | ✓ mit | 367 K | 9.5 GB |
| 358 | spark-s1-4b-v6-GGUF | 4.0 B | — | ✓ apache-2.0 | 367 K | 4.9 GB |
| 359 | Qwen3-4B-Thinking-2507 | 4.0 B | 262 K | ✓ apache-2.0 | 364 K | 10.0 GB |
| 360 | fullstop-punctuation-multilang-large | 560 M | 512 | ✓ mit | 363 K | 3.0 GB |
| 361 | gpt-oss-20b-GGUF | 20.0 B | 131 K | ✓ apache-2.0 | 356 K | 4.5 GB |
| 362 | roberta-base-openai-detector | 125 M | 512 | ✓ mit | 353 K | 1.1 GB |
| 363 | convnext_base.fb_in22k_ft_in1k | 90 M | — | ✓ apache-2.0 | 350 K | 0.9 GB |
| 364 | wide_resnet101_2.tv_in1k | 127 M | — | ✓ bsd-3-clause | 350 K | 1.1 GB |
| 365 | Meta-Llama-3.1-8B-Instruct-GGUF | — | — | ⚠ llama3.1 | 344 K | 3.7 GB |
| 366 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 338 K | 3.7 GB |
| 367 | mask2former-swin-large-ade-semantic | 220 M | — | other | 336 K | 1.5 GB |
| 368 | Pony_Diffusion_V6_XL | — | — | cdla-permissive-2.0 | 335 K | 8.5 GB |
| 369 | resnet-18 | 12 M | — | ✓ apache-2.0 | 333 K | 0.6 GB |
| 370 | Phi-4-mini-instruct | 3.8 B | 131 K | ✓ mit | 332 K | 9.5 GB |
| 371 | Ornith-1.5-9B-OBLITERATED | 9.7 B | — | ✓ mit | 332 K | 6.3 GB |
| 372 | convnextv2_large.fcmae_ft_in22k_in1k_384 | 200 M | — | ✗ cc-by-nc-4.0 | 327 K | 1.4 GB |
| 373 | Jan-v3.5-4B-gguf | — | — | ✓ apache-2.0 | 327 K | 2.8 GB |
| 374 | inclusively-classification | 110 M | 512 | ✗ cc-by-nc-sa-4.0 | 323 K | 1.0 GB |
| 375 | Meta-Llama-3.1-8B-Instruct-AWQ-INT4 | 8.0 B | 131 K | ⚠ llama3.1 | 321 K | 8.0 GB |
| 376 | Phi-3-mini-4k-instruct | 3.8 B | 4 K | ✓ mit | 321 K | 9.5 GB |
| 377 | Ornith-1.0-9B-AWQ-INT4 | 9.4 B | — | ✓ mit | 317 K | 11.8 GB |
| 378 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 315 K | 4.0 GB |
| 379 | regnety_032.ra_in1k | 20 M | — | ✓ apache-2.0 | 314 K | 0.6 GB |
| 380 | opus-mt-fr-en | 80 M | 512 | ✓ apache-2.0 | 312 K | 0.8 GB |
| 381 | macbert4csc-base-chinese | 100 M | 512 | ✓ apache-2.0 | 312 K | 1.0 GB |
| 382 | phishing-email-detection-distilbert_v2.4.1 | 70 M | 512 | ✓ apache-2.0 | 311 K | 0.8 GB |
| 383 | mms-lid-1024 | 967 M | — | ✗ cc-by-nc-4.0 | 308 K | 4.9 GB |
| 384 | Qwen3-1.7B | 2.0 B | 41 K | ✓ apache-2.0 | 306 K | 5.3 GB |
| 385 | prokbert-mini-promoter | 20 M | 1 K | ✗ cc-by-nc-4.0 | 302 K | 0.6 GB |
| 386 | vit_small_patch16_224.augreg_in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 302 K | 0.6 GB |
| 387 | pythia-14m | 10 M | 2 K | ✓ apache-2.0 | 299 K | 0.5 GB |
| 388 | nllb-200-3.3B | 3.3 B | 1 K | ✗ cc-by-nc-4.0 | 296 K | 8.3 GB |
| 389 | JiRackUltra_14b | 14.8 B | 131 K | ✓ mit | 292 K | 9.1 GB |
| 390 | voice-gender-classifier | 20 M | — | ✓ mit | 291 K | 0.6 GB |
| 391 | Qwen2.5-3B-Instruct-GGUF | — | — | other | 291 K | 2.0 GB |
| 392 | Qwen2.5-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 288 K | 3.6 GB |
| 393 | xflux_text_encoders | 4.8 B | — | ✓ apache-2.0 | 288 K | 11.7 GB |
| 394 | resnet50.fb_swsl_ig1b_ft_in1k | 26 M | — | ✗ cc-by-nc-4.0 | 288 K | 0.6 GB |
| 395 | segformer-b0-finetuned-ade-512-512 | <0.1 M | — | other | 286 K | 0.5 GB |
| 396 | gpt2-mini | 39 M | — | ✓ mit | 285 K | 0.7 GB |
| 397 | controlnet-openpose-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 285 K | 6.2 GB |
| 398 | LFM3-1.7B-GGUF | 1.7 B | — | other | 283 K | 1.9 GB |
| 399 | koelectra-small-v3-nsmc | 10 M | 512 | ✓ mit | 283 K | 0.6 GB |
| 400 | OpenMed-NER-PharmaDetect-SuperClinical-434M | 430 M | 512 | ✓ apache-2.0 | 279 K | 1.5 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.