Most Downloaded Models

Tracked models ranked by downloads over the rolling recent window reported by the source. How this is measured

#	Model	Task	DL 30D	7D	Likes	Params
1	GLM-5.2zai-org	Text Generation	2.7M	—	5,037	753B
2	gemma-4-26B-A4B-it-AWQ-4bitcyankiwi	Image Text to Text	2.7M	—	94	26.6B
3	siglip2-giant-opt-patch16-384google	Zero-Shot Image Classification	2.7M	—	43	1.9B
4	Qwen3.8-27B-FP8Qwen	Image Text to Text	2.7M	—	672	27.8B
5	all-MiniLM-L6-v2Xenova	Embeddings	2.7M	—	143	—
6	tiny-random-LlamaForCausalLMhmellor	Text Generation	2.6M	—	2	1.1M
7	Kronos-Tokenizer-baseNeoQuasar	Time Series Forecasting	2.6M	—	69	4M
8	nsfw-image-detection-largeTostAI	—	2.6M	—	24	87.1M
9	dinov2-basefacebook	Image Feature Extraction	2.6M	—	193	86.6M
10	Qwen3-30B-A3BQwen	Text Generation	2.6M	—	926	30.5B
11	embeddinggemma-300mgoogle	Sentence Similarity	2.6M	—	1,854	303M
12	wav2vec2-large-xlsr-53-dutchjonatasgrosman	Speech Recognition	2.6M	—	17	—
13	indonesian-roberta-base-posp-taggerw11wo	Token Classification	2.6M	—	10	124M
14	Qwen3.6-35B-A3B-NVFP4unsloth	Image Text to Text	2.6M	—	113	24.6B
15	llava-1.5-7b-hfllava-hf	Image Text to Text	2.6M	—	371	7.1B
16	all-distilroberta-v1sentence-transformers	Sentence Similarity	2.6M	—	43	82.1M
17	Qwen3-VL-2B-InstructQwen	Image Text to Text	2.6M	—	451	2.1B
18	koelectra-small-v3-nsmcdaekeun-ml	Text Classification	2.5M	—	7	14.1M
19	mms-300m-1130-forced-alignerMahmoudAshraf	Speech Recognition	2.5M	—	99	315M
20	Wan_2.1_ComfyUI_repackagedComfy-Org	—	2.5M	—	962	—
21	Qwen3-VL-8B-Instruct-FP8Qwen	Image Text to Text	2.5M	—	79	8.8B
22	bge-reranker-largeBAAI	Embeddings	2.5M	—	467	560M
23	chronos-2-smallautogluon	Time Series Forecasting	2.5M	—	4	27.9M
24	wav2vec2-indonesian-javanese-sundaneseindonesian-nlp	Speech Recognition	2.5M	—	15	—
25	Qwen3.5-35B-A3BQwen	Image Text to Text	2.5M	—	1,491	36B
26	Qwen3.6-27B-AWQ-INT4cyankiwi	Image Text to Text	2.5M	—	109	29.3B
27	Qwen3.6-35B-A3B-Uncensored-HauhauCS-AggressiveHauhauCS	Image Text to Text	2.5M	—	3,504	—
28	SmolLM2-135MHuggingFaceTB	Text Generation	2.4M	—	226	135M
29	Qwen2.5-Coder-7B-InstructQwen	Text Generation	2.4M	—	779	7.6B
30	fashion-clippatrickjohncyh	Zero-Shot Image Classification	2.4M	—	290	151M
31	DeepSeek-OCRdeepseek-ai	Image Text to Text	2.4M	—	3,347	3.3B
32	Qwen3.8-27BQwen	Image Text to Text	2.4M	—	12.3K	27.8B
33	granite-4.1-8bibm-granite	Text Generation	2.3M	—	253	8.8B
34	tiny-Qwen2ForSequenceClassification-2.5trl-internal-testing	Text Classification	2.3M	—	1	2.4M
35	Voxtral-Mini-4B-Realtime-2602mistralai	Speech Recognition	2.3M	—	950	4.4B
36	bge-small-en-v1.5michaelfeil	Embeddings	2.3M	—	3	33.4M
37	Gemma-4-E4B-Uncensored-HauhauCS-AggressiveHauhauCS	Image Text to Text	2.3M	—	1,023	—
38	Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen	Text to Speech	2.3M	—	1,902	1.9B
39	Qwen2.5-32B-InstructQwen	Text Generation	2.3M	—	355	32.8B
40	Gemma-4-31B-IT-NVFP4nvidia	Text Generation	2.3M	—	558	20.9B
41	distilgpt2distilbert	Text Generation	2.3M	—	637	88.2M
42	parakeet-tdt-0.6b-v2mlx-community	Speech Recognition	2.2M	—	45	618M
43	bge-base-en-v1.5Xenova	Embeddings	2.2M	—	10	—
44	TRELLIS-image-largemicrosoft	Image To 3d	2.2M	—	672	—
45	Qwen2.5-Coder-14B-InstructQwen	Text Generation	2.2M	—	181	14.8B
46	Qwen3-14B-AWQQwen	Text Generation	2.2M	—	74	14.8B
47	TinyLlama-1.1B-Chat-v1.0TinyLlama	Text Generation	2.2M	—	1,740	1.1B
48	multilingual-e5-large-instructintfloat	Embeddings	2.2M	—	633	560M
49	wav2vec2-large-xlsr-53-greekjonatasgrosman	Speech Recognition	2.2M	—	4	—
50	Qwen2.5-14B-Instruct-AWQQwen	Text Generation	2.2M	—	37	14.8B