AImodelsComparison.com 1,000 models
Menu
Models Best of Trending Can I run it? Methodology About
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.

Task
All text-generation 400 text-to-image 150 ASR 85 image-text-to-text 80 sentence-similarity 54 feature-extraction 46 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 15 audio-classification 12 image-segmentation 8 object-detection 8 summarization 7
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
$
1,000 models
#ModelParamsContextCommercial use30dMin VRAM
401 clap-htsat-unfused laion · feature-extraction — — ✓ apache-2.0 728 K —
402 NVIDIA-Nemotron-3-Nano-4B-BF16 nvidia · text-generation 4.0 B 262 K other 721 K from 9.8 GB
403 wav2vec2-xls-r-300m-mixed mesolitica · ASR — — unknown 719 K —
404 e5-small-v2 intfloat · sentence-similarity 30 M 512 ✓ mit 718 K from 0.7 GB
405 bert-base-multilingual-uncased-sentiment nlptown · text-classification 170 M 512 ✓ mit 710 K from 1.3 GB
406 sd-turbo stabilityai · text-to-image 870 M — unknown 708 K from 14.9 GB
407 Qwen2.5-32B-Instruct-AWQ Qwen · text-generation 32.8 B 33 K ✓ apache-2.0 707 K from 26.7 GB
408 Qwen3-30B-A3B-Instruct-2507-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 705 K from 21.2 GB
409 Qwen3-4B-Base Qwen · text-generation 4.0 B 33 K ✓ apache-2.0 703 K from 10.0 GB
410 Qwen3.6-27B-Text-NVFP4-MTP sakamakismile · text-generation 16.7 B — ✓ apache-2.0 701 K from 24.6 GB
411 BiRefNet ZhengPeng7 · image-segmentation 220 M — ✓ mit 692 K from 1.0 GB
412 punctuate-all kredor · token-classification — 512 ✓ mit 690 K —
413 NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 nvidia · text-generation 18.2 B 262 K other 688 K from 24.5 GB
414 nb-wav2vec2-1b-nynorsk NbAiLab · ASR 960 M — ✓ apache-2.0 688 K from 4.9 GB
415 parakeet-tdt-0.6b-v2 nvidia · ASR — — ✓ cc-by-4.0 687 K —
416 ruri-v3-310m cl-nagoya · sentence-similarity 310 M 8 K ✓ apache-2.0 687 K from 1.9 GB
417 vit_tiny_patch16_224.augreg_in21k_ft_in1k timm · image-classification 10 M — ✓ apache-2.0 685 K from 0.5 GB
418 MobileLLaMA-1.4B-Chat mtgv · text-generation — 2 K ✓ apache-2.0 685 K —
419 bert-large-cased-finetuned-conll03-english dbmdz · token-classification 330 M 512 unknown 684 K from 2.0 GB
420 whisper-tiny mlx-community · ASR — — unknown 678 K —
421 larger_clap_music_and_speech laion · feature-extraction — — ✓ apache-2.0 678 K —
422 Mistral-7B-v0.1 mistralai · text-generation 7.2 B 33 K ✓ apache-2.0 677 K from 17.5 GB
423 opus-mt-en-ru Helsinki-NLP · translation — 512 ✓ apache-2.0 677 K —
424 Ornith-1.0-397B-FP8 deepreinforce-ai · text-generation 397.0 B — ✓ mit 673 K from 505.7 GB
425 xlm-roberta-base-language-detection papluca · text-classification 280 M 512 ✓ mit 672 K from 1.8 GB
426 phi-4 microsoft · text-generation 14.7 B 16 K ✓ mit 671 K from 34.9 GB
427 RMBG-2.0 briaai · image-segmentation · gated 220 M — other 671 K from 1.5 GB
428 VibeVoice-ASR microsoft · ASR 8.7 B — ✓ mit 671 K from 20.9 GB
429 gemma-4-31B-it-NVFP4-turbo LilaRest · text-generation 32.5 B — ✓ apache-2.0 668 K from 26.6 GB
430 repvgg_a0.rvgg_in1k timm · image-classification 10 M — ✓ mit 665 K from 0.5 GB
431 wav2vec2-base-vi-vlsp2020 nguyenvulebinh · ASR — — ✗ cc-by-nc-4.0 664 K —
432 wav2vec2-large-xlsr-53-finnish jonatasgrosman · ASR — — ✓ apache-2.0 664 K —
433 turn-detector livekit · text-classification 130 M 8 K other 663 K from 1.1 GB
434 vit_base_patch8_224.augreg2_in21k_ft_in1k timm · image-classification 90 M — ✓ apache-2.0 658 K from 0.9 GB
435 Qwen3-0.6B-Base Qwen · text-generation 600 M 33 K ✓ apache-2.0 655 K from 1.9 GB
436 vit-base-nsfw-detector AdamCodd · image-classification 90 M — ✓ apache-2.0 643 K from 0.9 GB
437 gemma-2-2b-it google · text-generation · gated 2.6 B — ⚠ gemma 642 K from 6.6 GB
438 opus-mt-en-de Helsinki-NLP · translation — 512 ✓ cc-by-4.0 635 K —
439 VibeVoice-Realtime-0.5B microsoft · text-to-speech 1.0 B — ✓ mit 632 K from 2.9 GB
440 Qwen3-235B-A22B Qwen · text-generation 235.1 B 41 K ✓ apache-2.0 630 K from 553.0 GB
441 splade-cocondenser-ensembledistil naver · feature-extraction — 512 ✗ cc-by-nc-sa-4.0 629 K —
442 indobert-base-p1 indobenchmark · feature-extraction — 512 ✓ mit 628 K —
443 Ornith-1.0-397B-FP8 ornith-ai · text-generation 396.8 B — ✓ mit 627 K from 505.7 GB
444 wav2vec2-xls-r-300m-bengali arijitx · ASR — — ✓ apache-2.0 621 K —
445 OLMo-2-0425-1B allenai · text-generation 1.5 B 4 K ✓ apache-2.0 620 K from 7.3 GB
446 DeepSeek-V4-Flash-0731 deepseek-ai · text-generation 304.2 B 1.0 M ✓ mit 618 K from 229.7 GB
447 Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 607 K from 21.2 GB
448 parakeet-tdt-0.6b-v3-gguf handy-computer · ASR — — ✓ cc-by-4.0 605 K from 1.0 GB
449 Qwen3-32B-AWQ Qwen · text-generation 32.8 B 41 K ✓ apache-2.0 605 K from 26.7 GB
450 whisper-tiny.en Xenova · ASR — — ✓ apache-2.0 604 K —
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.