AImodelsComparison.com 1,058 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 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 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 Kokoro-82M-v1.0-ONNX onnx-community · text-to-speech 82 M — ✓ apache-2.0 720 K from 0.7 GB
402 ast-finetuned-audioset-10-10-0.4593 MIT · audio-classification 90 M — ✓ bsd-3-clause 719 K from 0.9 GB
403 distilbart-cnn-12-6 sshleifer · summarization — 1 K ✓ apache-2.0 718 K —
404 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation 6.9 B 4 K other 718 K from 16.7 GB
405 Qwen3-14B-NVFP4 nvidia · text-generation 8.2 B 41 K ✓ apache-2.0 713 K from 13.3 GB
406 wav2vec2-large-robust-12-ft-emotion-msp-dim audeering · audio-classification 170 M — ✗ cc-by-nc-sa-4.0 713 K from 1.3 GB
407 Qwen2-0.5B Qwen · text-generation 490 M 131 K ✓ apache-2.0 709 K from 1.7 GB
408 conv-bert-base YituTech · feature-extraction — 512 unknown 709 K —
409 resnet50.ram_in1k timm · image-classification 30 M — ✓ apache-2.0 709 K from 0.6 GB
410 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 708 K from 1.4 GB
411 Qwen2.5-Coder-7B Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 706 K from 18.4 GB
412 e5-base intfloat · sentence-similarity 110 M 512 ✓ mit 701 K from 1.0 GB
413 granite-4.1-30b ibm-granite · text-generation 28.9 B 131 K ✓ apache-2.0 700 K from 68.3 GB
414 Qwen3.8-27B-DFlash2-GGUF z-lab · text-generation — — ✓ apache-2.0 696 K from 1.8 GB
415 splade-cocondenser-selfdistil naver · feature-extraction — 512 ✗ cc-by-nc-sa-4.0 696 K —
416 Giga-Embeddings-instruct ai-sage · feature-extraction 3.5 B — ✓ mit 695 K from 16.2 GB
417 Qwen3.8-9B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 693 K from 6.9 GB
418 bert-base-multilingual-uncased-sentiment nlptown · text-classification 170 M 512 ✓ mit 689 K from 1.3 GB
419 Qwen2.5-7B Qwen · text-generation 7.6 B 131 K ✓ apache-2.0 687 K from 18.4 GB
420 LaBSE setu4993 · sentence-similarity 471 M 512 ✓ apache-2.0 687 K from 2.6 GB
421 wav2vec2-large-xlsr-53-gender-recognition-librispeech alefiury · audio-classification 320 M — ✓ apache-2.0 676 K from 1.9 GB
422 paraphrase-multilingual-MiniLM-L12-v2 Xenova · feature-extraction 120 M 512 unknown 675 K from 0.8 GB
423 wikineural-multilingual-ner Babelscape · token-classification 180 M 512 ✗ cc-by-nc-sa-4.0 675 K from 1.3 GB
424 Qwen1.5-MoE-A2.7B Qwen · text-generation 14.3 B 8 K other 673 K from 34.1 GB
425 Ornith-1.0-397B-FP8 deepreinforce-ai · text-generation 397.0 B — ✓ mit 673 K from 505.7 GB
426 parakeet-ctc-1.1b nvidia · ASR 1.1 B — ✓ cc-by-4.0 672 K from 2.0 GB
427 paraphrase-MiniLM-L3-v2 sentence-transformers · sentence-similarity 20 M 512 ✓ apache-2.0 668 K from 0.6 GB
428 NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 nvidia · text-generation 31.6 B 262 K other 666 K from 74.7 GB
429 gte-Qwen2-1.5B-instruct Alibaba-NLP · sentence-similarity 1.8 B 131 K ✓ apache-2.0 665 K from 8.6 GB
430 gemma-2-2b-it google · text-generation · gated 2.6 B — ⚠ gemma 663 K from 6.6 GB
431 Ternary-Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 663 K from 1.2 GB
432 opus-mt-en-ru Helsinki-NLP · translation — 512 ✓ apache-2.0 661 K —
433 GLM-5.3-Flash-GGUF unsloth · text-generation — — ✓ mit 661 K from 54.7 GB
434 Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech 910 M — ✓ apache-2.0 655 K from 3.4 GB
435 Z-Image-Turbo Tongyi-MAI · text-to-image 6.2 B — ✓ apache-2.0 653 K from 37.5 GB
436 gpt-neox-20b EleutherAI · text-generation 20.7 B 2 K ✓ apache-2.0 652 K from 49.0 GB
437 phi-4 microsoft · text-generation 14.7 B 16 K ✓ mit 651 K from 34.9 GB
438 stable-diffusion-v1-4 CompVis · text-to-image 860 M — ⚠ creativeml-openrail-m 650 K from 13.5 GB
439 wav2vec2-large-xlsr-malayalam gvs · ASR — — ✓ apache-2.0 649 K —
440 audiobox-aesthetics facebook · audio-classification 100 M — ✓ cc-by-4.0 637 K from 1.0 GB
441 Ornith-1.5-397B ornith-ai · text-generation 403.4 B — ✓ mit 636 K from 948.5 GB
442 nli-mpnet-base-v2 sentence-transformers · sentence-similarity 110 M 512 ✓ apache-2.0 635 K from 1.0 GB
443 Nemotron-3-Embed-1B-BF16 nvidia · sentence-similarity 1.1 B 262 K other 633 K from 3.2 GB
444 all-roberta-large-v1 sentence-transformers · sentence-similarity 360 M 512 ✓ apache-2.0 632 K from 2.1 GB
445 Qwen2.5-Coder-7B-Instruct-AWQ Orion-zhen · text-generation 7.6 B 33 K ✓ apache-2.0 623 K from 7.9 GB
446 RMBG-2.0 briaai · image-segmentation · gated 220 M — other 622 K from 1.5 GB
447 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation 3.1 B 524 K ✓ apache-2.0 616 K from 12.7 GB
448 gte-large thenlper · sentence-similarity 340 M 512 ✓ mit 616 K from 1.3 GB
449 SmolLM3-3B-Base HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 615 K from 7.7 GB
450 SmolLM3-3B HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 614 K from 7.7 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.