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
451 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation 1.8 B 131 K ✓ mit 603 K from 4.7 GB
452 bloom-560m bigscience · text-generation 560 M — ⚠ bigscience-bloom-rail-1.0 599 K from 1.8 GB
453 mask2former-swin-large-ade-semantic facebook · image-segmentation 220 M — other 598 K from 1.5 GB
454 Phi-3-mini-4k-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 597 K from 9.5 GB
455 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation 6.9 B 4 K other 594 K from 16.7 GB
456 Bonsai-27B-mlx-1bit prism-ml · text-generation 1.7 B — ✓ apache-2.0 594 K from 6.4 GB
457 Ternary-Bonsai-27B-mlx-2bit prism-ml · text-generation 2.6 B — ✓ apache-2.0 592 K from 10.2 GB
458 cryptobert ElKulako · text-classification 120 M 512 ✓ mit 589 K from 1.1 GB
459 conv-bert-base YituTech · feature-extraction — 512 unknown 589 K —
460 NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 nvidia · text-generation 31.6 B 262 K other 587 K from 41.2 GB
461 Qwen2.5-Coder-7B-Instruct-AWQ Orion-zhen · text-generation 7.6 B 33 K ✓ apache-2.0 586 K from 7.9 GB
462 Qwen3-30B-A3B-Instruct-2507-FP8 Qwen · text-generation 30.5 B 262 K ✓ apache-2.0 582 K from 39.4 GB
463 snowflake-arctic-embed-s Snowflake · sentence-similarity 30 M 512 ✓ apache-2.0 581 K from 0.7 GB
464 nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR 960 M — ✓ apache-2.0 580 K from 4.9 GB
465 encodec_24khz facebook · feature-extraction 20 M — unknown 577 K from 0.6 GB
466 LFM2.5-1.2B-Instruct LiquidAI · text-generation 1.2 B 128 K other 575 K from 3.3 GB
467 nsfw_image_detector Freepik · image-classification 90 M — ✓ mit 575 K from 0.7 GB
468 sentence-bert-base-ja-mean-tokens-v2 sonoisa · feature-extraction 110 M 512 cc-by-sa-4.0 573 K from 1.0 GB
469 Phi-4-multimodal-instruct microsoft · ASR 5.6 B 131 K ✓ mit 573 K from 15.4 GB
470 Qwen2-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 569 K from 18.4 GB
471 gpt2-medium openai-community · text-generation 380 M — ✓ mit 565 K from 2.2 GB
472 VLM2Vec-Full TIGER-Lab · text-generation 4.2 B 131 K ✓ apache-2.0 563 K from 10.2 GB
473 wav2vec2-xls-r-parlaspeech-hr classla · ASR 320 M — unknown 562 K from 1.9 GB
474 DeepSeek-V4-Flash-DSpark deepseek-ai · text-generation 165.3 B 1.0 M ✓ mit 561 K from 208.9 GB
475 Qwen3-Reranker-4B-W4A16-G128 boboliu · text-classification 4.1 B 41 K ✓ apache-2.0 561 K from 4.0 GB
476 MERT-v1-330M m-a-p · audio-classification — — ✗ cc-by-nc-4.0 559 K —
477 MiniMax-M3-NVFP4 nvidia · text-generation 246.6 B — other 551 K from 312.6 GB
478 DeepSeek-Coder-V2-Lite-Instruct deepseek-ai · text-generation 15.7 B 164 K other 546 K from 37.4 GB
479 msmarco-bert-base-dot-v5 sentence-transformers · sentence-similarity 110 M 512 unknown 544 K from 1.0 GB
480 deepseek-coder-6.7b-instruct deepseek-ai · text-generation 6.7 B 16 K other 542 K from 16.3 GB
481 Hermes-3-Llama-3.1-8B NousResearch · text-generation 8.0 B 131 K ⚠ llama3 542 K from 19.4 GB
482 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 542 K from 13.1 GB
483 wav2vec2-xlsr-nepali gagan3012 · ASR — — ✓ apache-2.0 542 K —
484 sat-3l-sm segment-any-text · token-classification 210 M 514 ✓ mit 541 K from 1.5 GB
485 ner-english-fast flair · token-classification — — unknown 539 K —
486 detr-resnet-50 facebook · object-detection 40 M 1 K ✓ apache-2.0 538 K from 0.7 GB
487 Qwen3-Coder-Next Qwen · text-generation 79.7 B 262 K ✓ apache-2.0 537 K from 187.7 GB
488 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation 9.2 B 8 K ⚠ gemma 535 K from 8.7 GB
489 Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen · text-to-speech 1.9 B — ✓ apache-2.0 533 K from 5.8 GB
490 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 533 K from 8.0 GB
491 macbert4csc-base-chinese shibing624 · text-generation 100 M 512 ✓ apache-2.0 531 K from 1.0 GB
492 whisper-bemba-stt AbelZimba · ASR 240 M — unknown 530 K from 1.6 GB
493 gte-base thenlper · sentence-similarity 110 M 512 ✓ mit 527 K from 0.8 GB
494 twitter-roberta-base-sentiment cardiffnlp · text-classification — 512 unknown 527 K —
495 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 527 K from 7.8 GB
496 privacy-filter openai · token-classification 1.4 B 131 K ✓ apache-2.0 525 K from 6.9 GB
497 FLUX.1-dev black-forest-labs · text-to-image · gated 11.9 B — other 523 K from 66.0 GB
498 EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation 7.8 B 33 K other 516 K from 36.1 GB
499 jina-embeddings-v5-text-nano jinaai · feature-extraction 210 M 8 K ✗ cc-by-nc-4.0 515 K from 1.1 GB
500 Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction 4.1 B 41 K ✓ apache-2.0 514 K from 4.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.