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
551 nsfw-image-detection-384 Marqo · image-classification Open weights 5.6 M — ✓ apache-2.0 433 K from 0.5 GB
552 wav2vec2-large-mms-1b-azerbaijani-common_voice15.0 nijatzeynalov · ASR Open weights 960 M — ✗ cc-by-nc-4.0 427 K from 4.9 GB
553 opus-mt-zh-en Helsinki-NLP · translation Open weights — 512 ✓ cc-by-4.0 426 K —
554 maple-preview-GGUF deepgrove · text-generation Open weights — — ✓ mit 424 K from 6.5 GB
555 wav2vec2-large-xls-r-300m-bg-d2 DrishtiSharma · ASR Open weights 300 M — ✓ apache-2.0 423 K from 1.2 GB
556 Voxtral-Mini-4B-Realtime-2602-gguf handy-computer · ASR Open weights 4.0 B — ✓ apache-2.0 421 K from 4.2 GB
557 Apertus-8B-Instruct-2509 swiss-ai · text-generation Open weights 8.1 B 66 K ✓ apache-2.0 421 K from 19.4 GB
558 Qwen3-30B-A3B-Instruct-2507-AWQ stelterlab · text-generation Open weights 30.8 B 262 K ✓ apache-2.0 419 K from 23.5 GB
559 glotlid cis-lmu · text-classification Open weights — — other 417 K —
560 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation Open weights 6.9 B 4 K other 417 K from 16.7 GB
561 pythia-6.9b EleutherAI · text-generation Open weights 7.0 B 2 K ✓ apache-2.0 414 K from 16.8 GB
562 Qwen2.5-Coder-1.5B-Instruct Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 409 K from 4.1 GB
563 gemma-4-31B-it-qat-NVFP4-Blackwell melcheikh · text-generation Open weights 31.0 B — ✓ apache-2.0 408 K from 27.6 GB
564 robertuito-sentiment-analysis pysentimiento · text-classification Open weights 110 M 128 unknown 404 K from 1.0 GB
565 Qwen3-235B-A22B Qwen · text-generation Open weights 235.1 B 41 K ✓ apache-2.0 404 K from 553.0 GB
566 Qwen3.8-27B-MTP-NVFP4 sakamakismile · text-generation Open weights 27.4 B — ✓ apache-2.0 398 K from 27.2 GB
567 saiga_llama3_8b IlyaGusev · text-generation Open weights 8.0 B 8 K other 396 K from 19.4 GB
568 DeepSeek-Coder-V2-Lite-Instruct deepseek-ai · text-generation Open weights 15.7 B 164 K other 394 K from 37.4 GB
569 GPT-OSS-20B-NPU2 FastFlowLM · text-generation Open weights 20.0 B 131 K ✓ apache-2.0 390 K from 47.5 GB
570 Ornith-1.0-397B deepreinforce-ai · text-generation Open weights 396.8 B — ✓ mit 387 K from 933.0 GB
571 Ling-3.0-tiny-MLX-4bit rapid-mlx · text-generation Open weights 7.9 B 131 K ✓ mit 386 K from 6.6 GB
572 japanese-gpt-neox-small rinna · text-generation Open weights 200 M 2 K ✓ mit 385 K from 1.3 GB
573 JEV-27B autotrust · text-classification Open weights 26.9 B 262 K ✓ apache-2.0 384 K from 64.7 GB
574 roberta-base-openai-detector openai-community · text-classification Open weights 125 M 512 ✓ mit 382 K from 1.1 GB
575 swinv2-tiny-patch4-window16-256 microsoft · image-classification Open weights — — ✓ apache-2.0 382 K —
576 Qwen2.5-Coder-1.5B Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 381 K from 4.1 GB
577 Qwen3.8-27B-NVFP4-MTP-GGUF esatapedico · text-generation Open weights 27.0 B — ✓ apache-2.0 381 K from 41.0 GB
578 Phi-3.5-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 376 K from 9.5 GB
579 RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata jimmy31chen · text-generation Open weights — — ✓ apache-2.0 374 K from 98.3 GB
580 Spark-X2.5-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 373 K from 4.0 GB
581 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation Open weights 9.2 B 8 K ⚠ gemma 371 K from 8.7 GB
582 cryptobert ElKulako · text-classification Open weights 120 M 512 ✓ mit 370 K from 1.1 GB
583 RMBG-2.0 briaai · image-segmentation · gated Open weights 221 M — other 369 K from 1.5 GB
584 Qwen3.8-27B-DFlash2 incoai · text-generation Open weights 1.9 B 262 K ✓ apache-2.0 369 K from 5.0 GB
585 GLM-5.3-GGUF unsloth · text-generation Open weights — — other 368 K from 52.0 GB
586 mistral-7b-v0.3-bnb-4bit unsloth · text-generation Open weights 7.5 B 33 K ✓ apache-2.0 367 K from 6.2 GB
587 phi-4 microsoft · text-generation Open weights Also via API 14.7 B 16 K ✓ mit 365 K from 34.9 GB
588 mask2former-swin-large-cityscapes-semantic facebook · image-segmentation Open weights 220 M — other 363 K from 1.5 GB
589 Qwen2.5-Coder-7B Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 363 K from 18.4 GB
590 DeepSeek-V4-Pro deepseek-ai · text-generation Open weights Also via API 1,598.8 B 1.0 M ✓ mit 361 K from 1,191.5 GB
591 deid_roberta_i2b2 obi · token-classification Open weights 350 M 512 ✓ mit 359 K from 2.1 GB
592 Meta-Llama-3-8B-Instruct meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3 355 K from 19.4 GB
593 Juggernaut-XL-v9 RunDiffusion · text-to-image Open weights — — ⚠ creativeml-openrail-m 355 K from 15.9 GB
594 DeepSeek-R1-0528-Qwen3-8B deepseek-ai · text-generation Open weights 8.2 B 131 K ✓ mit 354 K from 19.7 GB
595 MuQ-large-msd-iter OpenMuQ · audio-classification Open weights 330 M — ✗ cc-by-nc-4.0 354 K from 2.0 GB
596 AI-image-detector umm-maybe · image-classification Open weights — — ✓ cc-by-4.0 353 K —
597 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 351 K from 1.3 GB
598 DeepSeek-R1-Distill-Qwen-32B deepseek-ai · text-generation Open weights 32.8 B 131 K ✓ mit 350 K from 77.5 GB
599 mms-lid-1024 facebook · audio-classification Open weights 967 M — ✗ cc-by-nc-4.0 347 K from 4.9 GB
600 koelectra-polite-v1 circulus · text-classification Open weights — 512 unknown 347 K —
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.