1,000 models · refreshed nightly
All models
Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 551 | msmarco-distilbert-base-tas-b | 66 M | 512 | ✓ apache-2.0 | 463 K | from 0.8 GB |
| 552 | DeepSeek-Coder-V2-Lite-Instruct-GGUF | — | — | other | 461 K | from 7.1 GB |
| 553 | pplx-embed-v1-0.6b | 600 M | 33 K | ✓ mit | 461 K | from 3.2 GB |
| 554 | wav2vec2-xlsr-khmer | — | — | ✓ apache-2.0 | 458 K | — |
| 555 | mimi | 100 M | 8 K | ✓ cc-by-4.0 | 458 K | from 0.9 GB |
| 556 | MedCPT-Query-Encoder | 110 M | 512 | other | 454 K | from 1.0 GB |
| 557 | vietnamese-bi-encoder | 130 M | 256 | ✓ apache-2.0 | 454 K | from 1.1 GB |
| 558 | indic-conformer-600m-multilingual | 600 M | — | ✓ mit | 453 K | from 1.9 GB |
| 559 | vit_base_patch16_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 450 K | from 0.9 GB |
| 560 | gemma4-e4b-claims-comparison | 7.9 B | — | ⚠ gemma | 450 K | from 19.2 GB |
| 561 | vakyansh-wav2vec2-sanskrit-sam-60 | — | — | unknown | 449 K | — |
| 562 | Qwen3-8B-Base | 8.2 B | 33 K | ✓ apache-2.0 | 447 K | from 19.7 GB |
| 563 | Llama-2-7b-chat-hf | 6.7 B | — | ⚠ llama2 | 447 K | from 16.3 GB |
| 564 | wav2vec2-large-xlsr-kn | — | — | ✓ apache-2.0 | 447 K | — |
| 565 | mask2former-swin-large-cityscapes-semantic | 220 M | — | other | 444 K | from 1.5 GB |
| 566 | zeta-2.1-autoround-W4A16 | 2.2 B | 33 K | unknown | 444 K | from 7.6 GB |
| 567 | Voxtral-Mini-4B-Realtime-2602-gguf | — | — | ✓ apache-2.0 | 442 K | from 3.6 GB |
| 568 | Bonsai-27B-gguf | — | — | ✓ apache-2.0 | 440 K | from 1.2 GB |
| 569 | Laguna-S-2.1-NVFP4 | 117.6 B | 1.0 M | openmdw-1.1 | 436 K | from 127.8 GB |
| 570 | DeepSeek-R1-Distill-Qwen-1.5B | 1.8 B | 131 K | ✓ mit | 431 K | from 4.7 GB |
| 571 | vit_small_patch16_224.augreg_in21k_ft_in1k | 20 M | — | ✓ apache-2.0 | 430 K | from 0.6 GB |
| 572 | whisper-large-v3-turbo-german | 810 M | — | ✓ apache-2.0 | 428 K | from 2.4 GB |
| 573 | Qwen3-4B-GGUF | — | — | ✓ apache-2.0 | 428 K | from 3.2 GB |
| 574 | wav2vec2-large-mms-1b-azerbaijani-common_voice15.0 | 960 M | — | ✗ cc-by-nc-4.0 | 427 K | from 4.9 GB |
| 575 | Qwen2.5-3B-Instruct-AWQ | 3.4 B | 33 K | other | 427 K | from 4.0 GB |
| 576 | Ornith-1.0-35B-FP8 | 35.1 B | — | ✓ mit | 425 K | from 47.1 GB |
| 577 | maple-preview-GGUF | — | — | ✓ mit | 424 K | from 6.5 GB |
| 578 | Qwen-AgentWorld-35B-A3B-GGUF | — | — | ✓ apache-2.0 | 423 K | from 13.1 GB |
| 579 | Bangla-twoclass-Sentiment-Analyzer | 280 M | 512 | ✓ mit | 422 K | from 1.8 GB |
| 580 | MiniCPM5-2B | 2.5 B | 131 K | ✓ apache-2.0 | 421 K | from 6.4 GB |
| 581 | Qwen3-4B-Thinking-2507 | 4.0 B | 262 K | ✓ apache-2.0 | 420 K | from 10.0 GB |
| 582 | Qwen3.6-14B-A3B-FableVibes-GGUF | — | — | ✓ apache-2.0 | 419 K | from 6.4 GB |
| 583 | opus-mt-en-de | — | 512 | ✓ cc-by-4.0 | 418 K | — |
| 584 | Qwen-Image-Lightning | — | — | ✓ apache-2.0 | 418 K | from 72.6 GB |
| 585 | fasttext-language-identification | — | — | ✗ cc-by-nc-4.0 | 416 K | — |
| 586 | Mistral-7B-v0.1 | 7.2 B | 33 K | ✓ apache-2.0 | 415 K | from 17.5 GB |
| 587 | saiga_llama3_8b | 8.0 B | 8 K | other | 414 K | from 19.4 GB |
| 588 | GPT-OSS-20B-NPU2 | 20.0 B | 131 K | ✓ apache-2.0 | 411 K | from 47.5 GB |
| 589 | Ornith-1.5-35B-A3B | 36.0 B | — | ✓ mit | 410 K | from 85.0 GB |
| 590 | NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | 31.6 B | 262 K | other | 409 K | from 41.2 GB |
| 591 | Phi-3-mini-4k-instruct | 3.8 B | 4 K | ✓ mit | 407 K | from 9.5 GB |
| 592 | opus-mt-de-en | — | 512 | ✓ apache-2.0 | 405 K | — |
| 593 | Qwen3-8B-GGUF | — | — | ✓ apache-2.0 | 404 K | from 6.0 GB |
| 594 | gemma-2-9b-it-AWQ-INT4 | 9.2 B | 8 K | ⚠ gemma | 402 K | from 8.7 GB |
| 595 | Qwen2.5-VL-7B-Instruct-NVFP4 | 5.0 B | 128 K | other | 399 K | from 9.2 GB |
| 596 | EXAONE-3.5-7.8B-Instruct | 7.8 B | 33 K | other | 396 K | from 36.1 GB |
| 597 | jina-reranker-m0 | 2.4 B | 33 K | ✗ cc-by-nc-4.0 | 395 K | from 6.2 GB |
| 598 | gemma-3-270m | 270 M | — | ⚠ gemma | 395 K | from 1.1 GB |
| 599 | swinv2-tiny-patch4-window16-256 | — | — | ✓ apache-2.0 | 394 K | — |
| 600 | granite-4.1-3b | 3.4 B | 131 K | ✓ apache-2.0 | 393 K | from 8.5 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.