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)

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 10 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Context	Speed	Arch	Source
1	Distil-Bert-Base-Uncased-Hf	NLP	Text Generation	11.3M	—	27 MB	—	—	—	Qualcomm AI Hub
2	Albert-Base-V2-Hf	NLP	Text Generation	11.8M	—	28 MB	—	—	—	Qualcomm AI Hub
3	MiniLM-v2	NLP	Text Generation	22.7M	—	54 MB	—	—	—	Qualcomm AI Hub
4	Mobile-Bert-Uncased-Google	NLP	Text Generation	25.3M	—	61 MB	—	—	—	Qualcomm AI Hub
5	Electra-Bert-Base-Discrim-Google	NLP	Text Generation	109.0M	—	262 MB	—	—	—	Qualcomm AI Hub
6	Bert-Base-Uncased-Hf	NLP	Text Generation	110.0M	—	264 MB	—	—	—	Qualcomm AI Hub
7	Nomic-Embed-Text	NLP	Text Generation	137.0M	—	329 MB	—	—	—	Qualcomm AI Hub
8	IndusQ-1.1B	NLP	Text Generation	1.0B	—	2.3 GB	—	—	—	Qualcomm AI Hub
9	PLaMo-1B	NLP	Text Generation	1.0B	—	2.3 GB	—	—	—	Qualcomm AI Hub
10	Gemma-4-E2B-it	NLP	Text Generation	2.0B	—	4.7 GB	—	—	—	Qualcomm AI Hub