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.

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

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

1,023 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
501	FLUX.1-dev black-forest-labs · text-to-image · gated	11.9 B	—	other	523 K	from 66.0 GB
502	EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation	7.8 B	33 K	other	516 K	from 36.1 GB
503	jina-embeddings-v5-text-nano jinaai · feature-extraction	210 M	8 K	✗ cc-by-nc-4.0	515 K	from 1.1 GB
504	Qwen3-Embedding-4B-W4A16-G128 boboliu · feature-extraction	4.1 B	41 K	✓ apache-2.0	514 K	from 4.0 GB
505	emotion-english-distilroberta-base j-hartmann · text-classification	—	512	unknown	514 K	—
506	wavlm-large microsoft · feature-extraction	—	—	unknown	513 K	—
507	granite-speech-3.3-2b ibm-granite · ASR	3.0 B	—	✓ apache-2.0	513 K	from 13.9 GB
508	wav2vec2-xls-r-300m-ftspeech saattrupdan · ASR	320 M	—	other	510 K	from 1.9 GB
509	inclusively-classification E-MIMIC · text-classification	110 M	512	✗ cc-by-nc-sa-4.0	509 K	from 1.0 GB
510	whisper-medium-gguf handy-computer · ASR	—	—	✓ apache-2.0	508 K	from 1.1 GB
511	MedCPT-Cross-Encoder ncbi · text-classification	—	512	other	506 K	—
512	GLM-4.7-Flash-AWQ-4bit cyankiwi · text-generation	32.1 B	203 K	✓ mit	504 K	from 27.5 GB
513	jina-clip-v2 jinaai · feature-extraction	870 M	—	✗ cc-by-nc-4.0	502 K	from 2.5 GB
514	faster-whisper-medium Systran · ASR	—	—	✓ mit	500 K	—
515	wav2vec2-large-xlsr-53-gender-recognition-librispeech alefiury · audio-classification	320 M	—	✓ apache-2.0	500 K	from 1.9 GB
516	t5gemma-s-s-prefixlm google · text-generation · gated	310 M	—	⚠ gemma	499 K	from 1.2 GB
517	vit_base_patch16_224.augreg2_in21k_ft_in1k timm · image-classification	90 M	—	✓ apache-2.0	498 K	from 0.9 GB
518	MiMo-7B-RL XiaomiMiMo · text-generation	7.8 B	33 K	✓ mit	498 K	from 18.9 GB
519	DeepSeek-V2-Lite deepseek-ai · text-generation	15.7 B	164 K	other	493 K	from 37.4 GB
520	wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR	—	—	✓ cc-by-4.0	493 K	—
521	lambda unslothai · feature-extraction	—	—	unknown	488 K	from 0.5 GB
522	Qwen-AgentWorld-35B-A3B-GGUF unsloth · text-generation	—	—	✓ apache-2.0	486 K	from 13.1 GB
523	resnet34.a1_in1k timm · image-classification	20 M	—	✓ apache-2.0	486 K	from 0.6 GB
524	bert-base-turkish-cased-mean-nli-stsb-tr emrecan · sentence-similarity	110 M	512	✓ apache-2.0	484 K	from 1.0 GB
525	llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification	180 M	512	✓ apache-2.0	483 K	from 1.3 GB
526	fullstop-punctuation-multilang-large oliverguhr · token-classification	560 M	512	✓ mit	483 K	from 3.0 GB
527	NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 nvidia · text-generation	560.5 B	262 K	other	482 K	from 1,317.7 GB
528	Qwen2.5-32B-Instruct-GPTQ-Int4 Qwen · text-generation	32.8 B	33 K	✓ apache-2.0	482 K	from 26.7 GB
529	convnext_tiny.in12k_ft_in1k timm · image-classification	30 M	—	✓ apache-2.0	481 K	from 0.6 GB
530	xlm-emo-t MilaNLProc · text-classification	—	512	unknown	481 K	—
531	Llama-3.1-405B-FP8 meta-llama · text-generation · gated	405.9 B	—	⚠ llama3.1	479 K	from 597.3 GB
532	SmolLM2-360M-Instruct HuggingFaceTB · text-generation	360 M	8 K	✓ apache-2.0	479 K	from 1.4 GB
533	GLM-5.1-FP8 zai-org · text-generation	753.9 B	203 K	✓ mit	478 K	from 945.4 GB
534	Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation	7.6 B	33 K	✓ apache-2.0	477 K	from 7.8 GB
535	vietnamese-bi-encoder bkai-foundation-models · sentence-similarity	130 M	256	✓ apache-2.0	476 K	from 1.1 GB
536	wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR	320 M	—	✓ apache-2.0	476 K	from 1.9 GB
537	Realistic_Vision_V5.1_noVAE SG161222 · text-to-image	860 M	—	⚠ creativeml-openrail-m	473 K	from 19.4 GB
538	wide_resnet50_2.racm_in1k timm · image-classification	70 M	—	✓ apache-2.0	473 K	from 0.8 GB
539	Nemotron-3-Embed-1B-BF16 nvidia · sentence-similarity	1.1 B	262 K	other	469 K	from 3.2 GB
540	Qwen3Guard-Gen-4B Qwen · text-generation	4.4 B	33 K	✓ apache-2.0	467 K	from 10.9 GB
541	Meta-Llama-3.1-8B-Instruct-FP8 RedHatAI · text-generation	8.0 B	131 K	⚠ llama3.1	465 K	from 11.7 GB
542	typhoon2.5-qwen3-4b typhoon-ai · text-generation	4.0 B	262 K	✓ apache-2.0	461 K	from 10.0 GB
543	pplx-embed-v1-0.6b perplexity-ai · feature-extraction	600 M	33 K	✓ mit	461 K	from 3.2 GB
544	tiny-mixtral TitanML · text-generation	250 M	131 K	unknown	460 K	from 1.6 GB
545	bge-base-en BAAI · feature-extraction	110 M	512	✓ mit	458 K	from 1.0 GB
546	bert-portuguese-ner lfcc · token-classification	—	512	✓ mit	457 K	—
547	paraphrase-MiniLM-L12-v2 sentence-transformers · sentence-similarity	30 M	512	✓ apache-2.0	456 K	from 0.7 GB
548	wav2vec2-large-xlsr-catala softcatala · ASR	—	—	✓ apache-2.0	455 K	—
549	MedCPT-Query-Encoder ncbi · feature-extraction	110 M	512	other	454 K	from 1.0 GB
550	llama-3.3-70b-instruct-awq casperhansen · text-generation	70.6 B	131 K	⚠ llama3.3	452 K	from 54.8 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.