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
351 wavlm-base-plus microsoft · feature-extraction — — unknown 881 K —
352 opus-mt-fr-en Helsinki-NLP · translation 80 M 512 ✓ apache-2.0 881 K from 0.8 GB
353 Qwen2.5-1.5B Qwen · text-generation 1.5 B 131 K ✓ apache-2.0 878 K from 4.1 GB
354 Phi-tiny-MoE-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 878 K from 9.3 GB
355 Qwen2.5-1.5B-Instruct-AWQ Qwen · text-generation 1.8 B 33 K ✓ apache-2.0 877 K from 2.5 GB
356 dreamshaper-7 Lykon · text-to-image 860 M — ⚠ creativeml-openrail-m 876 K from 9.7 GB
357 wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR 320 M — ✓ apache-2.0 868 K from 1.9 GB
358 gemma-4-26B-A4B-it-QAT-MLX-4bit lmstudio-community · image-text-to-text 4.6 B — ✓ apache-2.0 868 K from 18.4 GB
359 Qwen3.6-27B-MLX-6bit lmstudio-community · image-text-to-text 6.4 B — ✓ apache-2.0 867 K from 26.5 GB
360 NVIDIA-Nemotron-3-Super-120B-A12B-BF16 nvidia · text-generation 123.6 B 262 K other 866 K from 291.0 GB
361 Qwen3-Coder-Next-FP8-dynamic RedHatAI · text-generation 79.8 B 262 K ✓ apache-2.0 864 K from 102.4 GB
362 wav2vec2-large-xlsr-korean kresnik · ASR 320 M — ✓ apache-2.0 861 K from 1.9 GB
363 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity 20 M 512 unknown 854 K from 0.6 GB
364 Qwen3-8B-FP8 Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 853 K from 12.1 GB
365 specter2_base allenai · feature-extraction — 512 ✓ apache-2.0 853 K —
366 SmolLM3-3B HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 852 K from 7.7 GB
367 pubmedbert-base-embeddings NeuML · sentence-similarity 110 M 512 ✓ apache-2.0 852 K from 1.0 GB
368 distilbart-cnn-12-6 sshleifer · summarization — 1 K ✓ apache-2.0 829 K —
369 gte-small thenlper · sentence-similarity 30 M 512 ✓ mit 829 K from 0.6 GB
370 OmniVoice k2-fsa · text-to-speech 610 M — unknown 823 K from 4.2 GB
371 VoxCPM2 openbmb · text-to-speech 2.3 B — ✓ apache-2.0 818 K from 5.9 GB
372 llama-nemotron-embed-1b-v2 nvidia · feature-extraction 1.2 B 131 K other 816 K from 3.4 GB
373 text2vec-base-chinese shibing624 · sentence-similarity 100 M 512 ✓ apache-2.0 802 K from 1.0 GB
374 PP-DocLayoutV3_safetensors PaddlePaddle · object-detection 30 M — ✓ apache-2.0 801 K from 0.7 GB
375 mamba-130m-hf state-spaces · text-generation 130 M — unknown 800 K from 1.1 GB
376 bge-small-en-v1.5-onnx-Q Qdrant · sentence-similarity — 512 ✓ apache-2.0 799 K —
377 mimi kyutai · feature-extraction 100 M 8 K ✓ cc-by-4.0 796 K from 0.9 GB
378 Flux2-Klein-9B-True-V2 wikeeyang · text-to-image — — other 796 K from 6.8 GB
379 DeepSeek-R1-Distill-Qwen-14B deepseek-ai · text-generation 14.8 B 131 K ✓ mit 790 K from 35.2 GB
380 Llama-3.1-70B-Instruct meta-llama · text-generation · gated 70.6 B — ⚠ llama3.1 784 K from 166.3 GB
381 finbert-tone yiyanghkust · text-classification — 512 unknown 781 K —
382 phi-2 microsoft · text-generation 2.8 B 2 K ✓ mit 776 K from 7.0 GB
383 Ternary-Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 775 K from 1.2 GB
384 pythia-70m-deduped EleutherAI · text-generation 100 M 2 K ✓ apache-2.0 772 K from 0.7 GB
385 Qwen2.5-1.5B-quantized.w8a8 RedHatAI · text-generation 1.8 B 33 K ✓ apache-2.0 769 K from 3.2 GB
386 Llama-3.2-1B-Instruct-FP8 RedHatAI · text-generation 1.5 B 131 K ⚠ llama3.2 765 K from 3.0 GB
387 vntl-llama3-8b-v2-gguf lmg-anon · translation — — ⚠ llama3 761 K from 6.8 GB
388 Llama-2-7b-hf meta-llama · text-generation · gated 6.7 B — ⚠ llama2 761 K from 16.3 GB
389 F5-TTS SWivid · text-to-speech — — ✗ cc-by-nc-4.0 759 K from 5.0 GB
390 wav2vec2-xls-r-300m-hebrew imvladikon · ASR 320 M — unknown 754 K from 1.9 GB
391 DeepSeek-R1-Distill-Qwen-32B deepseek-ai · text-generation 32.8 B 131 K ✓ mit 752 K from 77.5 GB
392 vakyansh-wav2vec2-tamil-tam-250 Harveenchadha · ASR — — ✓ mit 752 K —
393 w2v-xls-r-uk Yehor · ASR 320 M — ✓ apache-2.0 750 K from 1.9 GB
394 wav2vec2-large-robust-12-ft-emotion-msp-dim audeering · audio-classification 170 M — ✗ cc-by-nc-sa-4.0 749 K from 1.3 GB
395 Llama-2-7b-chat-hf meta-llama · text-generation · gated 6.7 B — ⚠ llama2 745 K from 16.3 GB
396 KR-SBERT-V40K-klueNLI-augSTS snunlp · sentence-similarity — 512 unknown 743 K —
397 LaBSE sentence-transformers · sentence-similarity 470 M 512 ✓ apache-2.0 740 K from 2.6 GB
398 MiniMax-M2.5 MiniMaxAI · text-generation 228.7 B 197 K other 739 K from 288.0 GB
399 Qwen2.5-Coder-1.5B-Instruct Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 731 K from 4.1 GB
400 yolos-small hustvl · object-detection 30 M — ✓ apache-2.0 731 K from 0.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.