Small Model Hub

3,618 efficient AI models across 9 domains · Charts · API

Domain

All (3,618)Vision (1,615)3D (743)Embedding (472)Multimodal (305)Edge/Mobile (172)Code (125)Speech (89)Video (49)NLP (48)

Task

All Tasks Speech Recognition (67)Speech (13)audio generation (6)Image Classification (2)voice activity detection (1)

Max Size≤10M ≤50M ≤100M ≤500M All

Max VRAM≤512MB ≤1GB ≤2GB ≤4GB ≤8GB All

Score

Raw Context (0-100)

Percentile rank within each task — comparable across domains

Showing 7 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Context	Speed	Arch	Source
1	Silero-VAD	Speech	voice activity detection	0.24M	—	1 MB	—	—	—	Qualcomm AI Hub
2	YamNet	Speech	Image Classification	3.73M	—	9 MB	—	—	—	Qualcomm AI Hub
3	abr-ai/niagara-9m-batch.en	Speech	Speech Recognition	9.00M	—	22 MB	—	7158 RTFx	State-space model/CTC	Open ASR
4	abr-ai/niagara-19m-batch.en	Speech	Speech Recognition	20.0M	—	48 MB	—	4324 RTFx	State-space model/CTC	Open ASR
5	abr-ai/niagara-38m-batch.en	Speech	Speech Recognition	38.0M	—	91 MB	—	4015 RTFx	—	Open ASR
6	DeepSpeech2	Speech	Speech	94.6M	—	227 MB	—	—	—	Qualcomm AI Hub
7	HuggingFace-WavLM-Base-Plus	Speech	Speech	95.1M	—	228 MB	—	—	—	Qualcomm AI Hub