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 Image Classification (46)Object Detection (41)Segmentation (34)Pose Estimation (11)Super Resolution (10)driver assistance (9)image editing (6)Depth Estimation (6)image generation (4)video object tracking (2)robotics (1)gaze estimation (1)video generation (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 9 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Context	Speed	Arch	Source
1	GKT	Edge/Mobile	driver assistance	1.18M	—	3 MB	—	—	—	Qualcomm AI Hub
2	CVT	Edge/Mobile	driver assistance	1.33M	—	3 MB	—	—	—	Qualcomm AI Hub
3	CenterNet-3D	Edge/Mobile	driver assistance	20.6M	—	49 MB	—	—	—	Qualcomm AI Hub
4	CenterPoint	Edge/Mobile	driver assistance	21.8M	—	52 MB	—	—	—	Qualcomm AI Hub
5	BEVFormer	Edge/Mobile	driver assistance	27.0M	—	65 MB	—	—	—	Qualcomm AI Hub
6	BEVDet	Edge/Mobile	driver assistance	44.0M	—	106 MB	—	—	—	Qualcomm AI Hub
7	BEVFusion	Edge/Mobile	driver assistance	44.0M	—	106 MB	—	—	—	Qualcomm AI Hub
8	StateTransformer	Edge/Mobile	driver assistance	90.7M	—	218 MB	—	—	—	Qualcomm AI Hub
9	RangeNet-Plus-Plus	Edge/Mobile	driver assistance	—	—	—	—	—	—	Qualcomm AI Hub