AImodelsComparison.com 1,023 models
Menu
Models Best of Trending Can I run it? Methodology About
1,023 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 151 ASR 89 image-text-to-text 84 sentence-similarity 57 feature-extraction 48 translation 47 text-classification 39 image-classification 33 token-classification 23 text-to-speech 17 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
$
1,023 models
#ModelParamsContextCommercial use30dMin VRAM
601 rtdetr_r101vd_coco_o365 PekingU · object-detection 80 M — ✓ apache-2.0 404 K from 0.9 GB
602 EXAONE-3.5-7.8B-Instruct-AWQ LGAI-EXAONE · text-generation 7.8 B 33 K other 401 K from 7.5 GB
603 MiMo-V2.5 XiaomiMiMo · text-generation 310.8 B 1.0 M ✓ mit 398 K from 394.4 GB
604 Meta-Llama-3.1-8B-Instruct unsloth · text-generation 8.0 B 131 K ⚠ llama3.1 398 K from 19.4 GB
605 wav2vec2-large-xlsr-lithuanian m3hrdadfi · ASR — — ✓ apache-2.0 395 K —
606 Vikhr-Nemo-12B-Instruct-R-21-09-24 Vikhrmodels · text-generation 12.3 B 1.0 M ✓ apache-2.0 394 K from 30.8 GB
607 Ornith-1.0-397B deepreinforce-ai · text-generation 396.8 B — ✓ mit 387 K from 933.0 GB
608 wav2vec2-large-xlsr-kazakh aismlv · ASR 320 M — ✓ apache-2.0 386 K from 1.9 GB
609 GLM-5.2-AWQ-INT4 cyankiwi · text-generation 753.3 B 1.0 M ✓ mit 385 K from 635.1 GB
610 wav2vec2-xls-r-300m-sk-cv8 comodoro · ASR — — ✓ apache-2.0 383 K —
611 s2-pro fishaudio · text-to-speech 4.6 B — other 383 K from 11.2 GB
612 MOSS-TTS OpenMOSS-Team · text-to-speech 8.5 B — ✓ apache-2.0 375 K from 20.5 GB
613 playground-v2.5-1024px-aesthetic playgroundai · text-to-image 2.6 B — other 373 K from 46.7 GB
614 DeepSeek-R1-Distill-Llama-8B deepseek-ai · text-generation 8.0 B 131 K ✓ mit 372 K from 19.4 GB
615 fasttext-language-identification facebook · text-classification — — ✗ cc-by-nc-4.0 369 K —
616 mistral-7b-v0.3-bnb-4bit unsloth · text-generation 7.5 B 33 K ✓ apache-2.0 368 K from 6.2 GB
617 higgs-tts-2-3b-base bosonai · text-to-speech 5.8 B 2 K other 368 K from 14.1 GB
618 GigaAM-v3 ai-sage · ASR — — ✓ mit 366 K —
619 Ilama-3.2-1B hmellor · text-generation 1.2 B 131 K unknown 365 K from 6.1 GB
620 VieNeu-TTS-v3-Turbo pnnbao-ump · text-to-speech 130 M 1 K ✓ apache-2.0 364 K from 1.1 GB
621 parakeet-tdt-0.6b-v3-coreml FluidInference · ASR — — ✓ cc-by-4.0 363 K —
622 bert-small-pii-detection gravitee-io · token-classification 30 M 512 ✓ apache-2.0 363 K from 0.6 GB
623 convnext_femto.d1_in1k timm · image-classification 10 M — ✓ apache-2.0 363 K from 0.5 GB
624 Apertus-8B-Instruct-2509 swiss-ai · text-generation 8.1 B 66 K ✓ apache-2.0 362 K from 19.4 GB
625 speaker-diarization pyannote · ASR · gated — — ✓ mit 360 K —
626 whisper-medium openai · ASR 760 M — ✓ apache-2.0 358 K from 4.0 GB
627 Ornith-1.0-397B ornith-ai · text-generation 396.8 B — ✓ mit 358 K from 933.0 GB
628 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 358 K from 1.4 GB
629 segformer-b0-finetuned-ade-512-512 nvidia · image-segmentation 0 M — other 357 K from 0.5 GB
630 multilingual-sentiment-analysis tabularisai · text-classification 140 M 512 ✗ cc-by-nc-4.0 353 K from 1.1 GB
631 Fanar-1-9B-Instruct QCRI · text-generation 8.8 B 4 K ✓ apache-2.0 353 K from 21.1 GB
632 higgs-tts-3-4b bosonai · text-to-speech 4.7 B — other 349 K from 11.4 GB
633 wav2vec2-large-xlsr-malayalam gvs · ASR — — ✓ apache-2.0 349 K —
634 Qwen3.5-397B-A17B-NVFP4 nvidia · text-generation — — ✓ apache-2.0 347 K from 276.8 GB
635 Qwen3-4B-Thinking-2507 Qwen · text-generation 4.0 B 262 K ✓ apache-2.0 347 K from 10.0 GB
636 Apertus-70B-Instruct-2509-quantized.w4a16 RedHatAI · text-generation 11.3 B 66 K ✓ apache-2.0 346 K from 46.0 GB
637 gpt-oss-20b-MXFP4-Q8 mlx-community · text-generation 20.9 B 131 K ✓ apache-2.0 344 K from 16.9 GB
638 MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 344 K from 1.3 GB
639 gemma-3-270m-it google · text-generation · gated 270 M — ⚠ gemma 344 K from 1.1 GB
640 gpt-neo-125m EleutherAI · text-generation 150 M 2 K ✓ mit 343 K from 1.1 GB
641 segformer-b2-finetuned-ade-512-512 nvidia · image-segmentation — — other 338 K —
642 Llama-2-7b-hf NousResearch · text-generation 6.7 B 4 K unknown 335 K from 16.3 GB
643 NVIDIA-Nemotron-Nano-12B-v2 nvidia · text-generation 12.3 B — other 331 K from 29.4 GB
644 Qwen3-Next-80B-A3B-Instruct-FP8 Qwen · text-generation 81.3 B 262 K ✓ apache-2.0 330 K from 103.0 GB
645 Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen · text-generation 480.2 B 262 K ✓ apache-2.0 327 K from 602.9 GB
646 T-lite-it-2.1 t-tech · text-generation 8.2 B 41 K ✓ apache-2.0 327 K from 19.7 GB
647 GLM-4.5-Air unsloth · text-generation 110.5 B 131 K ✓ mit 325 K from 260.1 GB
648 Mistral-7B-Instruct-v0.2-AWQ TheBloke · text-generation 7.2 B 33 K ✓ apache-2.0 325 K from 6.2 GB
649 ms-marco-MiniLM-L-6-v2 Xenova · text-classification — 512 unknown 324 K —
650 FinancialBERT-Sentiment-Analysis ahmedrachid · text-classification — 512 unknown 323 K —
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.