AImodelsComparison.com 1,086 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,086 models · 1,086 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.

Type
All 1,286 Open weights (self-host) 1,086 API-only 200
Task
All text-generation 461 text-to-image 150 image-text-to-text 101 ASR 83 sentence-similarity 56 translation 46 feature-extraction 44 text-classification 43 image-classification 36 token-classification 17 text-to-speech 17 audio-classification 9 image-segmentation 8 object-detection 7 summarization 6 audio-text-to-text 1 any-to-any 1
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
1,086 models
#ModelParamsContextCommercial use30dMin VRAM
401 bge-small-en-v1.5 Xenova · feature-extraction Open weights 30 M 512 unknown 670 K from 0.6 GB
402 Laguna-XS.2 poolside · text-generation Open weights 33.4 B 262 K ✓ apache-2.0 669 K from 79.1 GB
403 VibeVoice-ASR microsoft · ASR Open weights 8.7 B — ✓ mit 669 K from 20.9 GB
404 Laguna-M.1 poolside · text-generation Open weights 225.8 B 262 K ✓ apache-2.0 668 K from 531.1 GB
405 Qwen3.5-397B-A17B Qwen · image-text-to-text Open weights Also via API 403.4 B — ✓ apache-2.0 667 K from 948.5 GB
406 efficientnet_b0.ra_in1k timm · image-classification Open weights 10 M — ✓ apache-2.0 662 K from 0.5 GB
407 Qwen3-4B-Thinking-2507 Qwen · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 662 K from 10.0 GB
408 wav2vec2-large-xlsr-malayalam gvs · ASR Open weights — — ✓ apache-2.0 660 K —
409 DeepSeek-V3-0324 deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 660 K from 860.6 GB
410 whisper-medium-gguf handy-computer · ASR Open weights 760 M — ✓ apache-2.0 655 K from 1.2 GB
411 deberta-v3-base-prompt-injection-v2 protectai · text-classification Open weights 180 M 512 ✓ apache-2.0 652 K from 1.3 GB
412 Qwen2.5-1.5B Qwen · text-generation Open weights 1.5 B 131 K ✓ apache-2.0 650 K from 4.1 GB
413 llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification Open weights 180 M 512 ✓ apache-2.0 641 K from 1.3 GB
414 Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech Open weights 910 M — ✓ apache-2.0 638 K from 3.4 GB
415 Qwen3-0.6B-Base Qwen · text-generation Open weights 600 M 33 K ✓ apache-2.0 637 K from 1.9 GB
416 FLUX.1-dev black-forest-labs · text-to-image · gated Open weights 11.9 B — other 631 K from 66.0 GB
417 nli-mpnet-base-v2 sentence-transformers · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 629 K from 1.0 GB
418 LaBSE sentence-transformers · sentence-similarity Open weights 470 M 512 ✓ apache-2.0 627 K from 2.6 GB
419 LFM2.5-2.6B-GGUF LiquidAI · text-generation Open weights 2.6 B 131 K other 627 K from 2.6 GB
420 wav2vec2-large-xlsr-53-gender-recognition-librispeech alefiury · audio-classification Open weights 320 M — ✓ apache-2.0 626 K from 1.9 GB
421 sdxl-turbo stabilityai · text-to-image Open weights 2.6 B — other 623 K from 46.7 GB
422 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity Open weights 20 M 512 unknown 615 K from 0.6 GB
423 JEV-9B autotrust · text-classification Open weights 9.0 B 262 K ✓ apache-2.0 611 K from 22.1 GB
424 granite-4.1-3b ibm-granite · text-generation Open weights 3.4 B 131 K ✓ apache-2.0 609 K from 8.5 GB
425 Llama-3.1-8B meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3.1 607 K from 19.4 GB
426 wav2vec2-xlsr-53-espeak-cv-ft facebook · ASR Open weights — — ✓ apache-2.0 601 K —
427 bge-small-en-v1.5 michaelfeil · feature-extraction Open weights 30 M 512 ✓ mit 599 K from 0.7 GB
428 Qwen3-4B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 597 K from 3.2 GB
429 Qwen3-8B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 597 K from 6.0 GB
430 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation Open weights 3.1 B 524 K ✓ apache-2.0 595 K from 12.7 GB
431 opus-mt-fr-en Helsinki-NLP · translation Open weights 80 M 512 ✓ apache-2.0 594 K from 0.8 GB
432 punctuate-all kredor · token-classification Open weights — 512 ✓ mit 592 K —
433 wikineural-multilingual-ner Babelscape · token-classification Open weights 180 M 512 ✗ cc-by-nc-sa-4.0 592 K from 1.3 GB
434 wav2vec2-large-xlsr-lithuanian m3hrdadfi · ASR Open weights — — ✓ apache-2.0 591 K —
435 vietnamese-bi-encoder bkai-foundation-models · sentence-similarity Open weights 130 M 256 ✓ apache-2.0 587 K from 1.1 GB
436 paraphrase-albert-small-v2 sentence-transformers · sentence-similarity Open weights 10 M 512 ✓ apache-2.0 583 K from 0.6 GB
437 parakeet-tdt-0.6b-v3 nvidia · ASR Open weights 630 M — ✓ cc-by-4.0 583 K from 1.4 GB
438 Qwen3-4B-Base Qwen · text-generation Open weights 4.0 B 33 K ✓ apache-2.0 578 K from 10.0 GB
439 clipseg-rd64-refined CIDAS · image-segmentation Open weights 150 M — ✓ apache-2.0 577 K from 1.2 GB
440 distilbert-base-multilingual-cased-sentiments-student lxyuan · text-classification Open weights 140 M 512 ✓ apache-2.0 577 K from 1.1 GB
441 whisper-tiny Xenova · ASR Open weights 40 M — ✓ apache-2.0 575 K from 0.6 GB
442 all-roberta-large-v1 sentence-transformers · sentence-similarity Open weights 360 M 512 ✓ apache-2.0 575 K from 2.1 GB
443 paraphrase-MiniLM-L3-v2 sentence-transformers · sentence-similarity Open weights 20 M 512 ✓ apache-2.0 574 K from 0.6 GB
444 Qwen3-1.7B-Base Qwen · text-generation Open weights 1.7 B 33 K ✓ apache-2.0 573 K from 4.5 GB
445 Qwen3-TTS-GGUF Serveurperso · text-to-speech Open weights — — ✓ apache-2.0 573 K from 1.8 GB
446 e5-mistral-7b-instruct-bnb-4bit gabor-hosu · feature-extraction Open weights 7.3 B 33 K ✓ mit 572 K from 5.8 GB
447 KURE-v1 nlpai-lab · feature-extraction Open weights 568 M 8 K ✓ mit 568 K from 3.1 GB
448 repvgg_a0.rvgg_in1k timm · image-classification Open weights 10 M — ✓ mit 566 K from 0.5 GB
449 gte-large thenlper · sentence-similarity Open weights 340 M 512 ✓ mit 564 K from 1.3 GB
450 Laguna-XS-2.1 poolside · text-generation Open weights Also via API 33.4 B 262 K openmdw-1.1 562 K from 79.1 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.