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	asr-conformer-transformerlm-librispeechspeechbrain	Speech Recognition	60	0.1%(up)	7	—
2	QwQ-32B-Preview-gptqmodel-4bit-vortex-v1ModelCloud	Text Generation	59	0.8%(up)	51	32.8B
3	Qwen2.5-VL-7B-Abliterated-Caption-itprithivMLmods	Image Text to Text	59	0.1%(up)	53	8.3B
4	llmjp-4-vl-9b-mlx-4bitmlx-community	Image Text to Text	59	—	0	9B
5	amoral-gemma3-12B-v2soob3123	Text Generation	59	0.2%(up)	49	12.2B
6	nb-sami-asr-north-parakeetNbAiLab	Speech Recognition	59	—	0	—
7	Fun-ASR-Nano-2512litert-community	Speech Recognition	59	—	5	—
8	Claire-7B-0.1OpenLLM-France	Text Generation	59	0.2%(up)	47	6.9B
9	mformer-carejoshnguyen	Text Classification	59	0%	2	—
10	SpatialGen-1.0manycore-research	Image To 3d	59	—	44	917M
11	UIGEN-X-8BTesslate	Text Generation	59	—	67	8.2B
12	s2t-wav2vec2-large-en-defacebook	Speech Recognition	59	0.0%(up)	4	—
13	Gemma-3-R1984-4BVIDraft	Image Text to Text	59	0.2%(up)	133	4.3B
14	piccolo-large-zhsensenova	Embeddings	59	0.1%(up)	69	—
15	roberta-large-qa-evaluatorzli12321	Text Classification	59	0.0%(up)	1	355M
16	llm-jp-4-vl-9b-mlx-4bitmlx-community	Image Text to Text	59	—	0	9B
17	Kartoffelbox-v0.1SebastianBodza	Text to Speech	59	—	82	—
18	pingala-v1-universalshunyalabs	Speech Recognition	59	0%	34	809M
19	a3-rl-DCAgent_mix_h4_binary_easy-50-8Blaion	—	58	—	0	8.2B
20	wav2vec2-large-xlsr-ksponspeech_1-20cheulyop	Speech Recognition	58	0%	2	—
21	Lumo-1-1.5B-Chat-GGUFmradermacher	—	58	—	0	—
22	ESMC-600M-sae-layer27-k16-codebook65536biohub	Embeddings	58	—	0	—
23	hebEMO_joyavichr	Text Classification	58	0.0%(up)	0	—
24	octo-netNexaAI	Text Generation	58	0.3%(up)	143	3.8B
25	Nano-Math-1.5Bv2KiteFishAI	Text Generation	58	0%	1	1.6B
26	e5-largeXenova	Embeddings	58	0.6%(up)	0	—
27	Llama-3.3-70B-Instruct-FP8-Blockunsloth	Text Generation	58	—	1	70.6B
28	Step-Audio-R1stepfun-ai	Audio Text To Text	58	0.3%(up)	144	33.5B
29	Llama-3.1-Nemotron-70B-Instructnvidia	—	58	0.0%(up)	570	—
30	qwen3_vit_306m_enc.qwen_drive_1_0_4btimm	Image Feature Extraction	58	—	0	333M
31	granite-geospatial-oceanibm-granite	—	58	0%	12	—
32	Gemma4-12B-Uncensoredtoandev	Any to Any	58	0.0%(up)	3	12B
33	Gen-Searcher-8BGenSearcher	Image Text to Text	58	0.3%(up)	30	8.8B
34	hua-1.7b-GGUFmradermacher	Reinforcement Learning	58	—	0	—
35	qwen3-asr-0.6b-onnx-int4rhasspy	Speech Recognition	58	—	0	—
36	ArrowPro-7B-KUJIRADataPilot	Text Generation	58	0.3%(up)	64	7.2B
37	ViCLIP-L-14-BVD-V-50M-s50M-b32Klaion	Video Classification	58	—	1	428M
38	emotion-diarization-wavlm-largespeechbrain	Audio Classification	58	0.0%(up)	57	—
39	Kev-0.8B-LiteRTlitert-community	Text Classification	58	—	3	—
40	samantha-mistral-instruct-7bQuixiAI	Text Generation	58	—	38	—
41	orato-asr-hindi-v1tryorato	Speech Recognition	58	0.7%(up)	30	782M
42	LWM-Text-Chat-1MLargeWorldModel	Text Generation	58	0.0%(up)	173	—
43	Supra-1.5-50M-Instruct-exp-ONNXonnx-community	Text Generation	58	—	4	—
44	nb-whisper-base-betaNbAiLab	Speech Recognition	58	0.4%(up)	1	72.6M
45	Laguna-XS-2.1-JANG_2L-CRACKdealignai	Text Generation	58	—	0	33.4B
46	EkmanClassifierarpanghoshal	Text Classification	58	0.0%(up)	11	—
47	MiniMax-M2.5-JANG_3L-CRACKdealignai	Text Generation	57	0%	3	116B
48	Fun-CineForgeFunAudioLLM	Text to Speech	57	—	63	—
49	Qwen2-7B-Multilingual-RPmaywell	Text Generation	57	0.0%(up)	58	7.6B
50	ms-marco-MiniLM-L-6-v2navteca	Text Classification	57	0%	2	—