Small Model Hub

3,378 efficient AI models across 7 domains · Charts · API

Domain

All (3,378)Vision (1,615)3D (771)Embedding (428)Multimodal (299)Code (125)Speech (91)Video (49)

Task

All Tasks Image Classification (1,543)3D Object Detection (771)Text Embedding (428)Vision-Language (285)Code Generation (125)Speech Recognition (91)Object Detection (65)Video Understanding (49)UI Understanding (14)Font Identification (7)

Max Size≤10M ≤50M ≤100M ≤500M All

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

Score

Raw Context (0-100)

Raw benchmark score — scale varies by task

Showing 13 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Score	Speed	Arch	Source
1	SmolVLM-256M	Multimodal	Vision-Language	260.0M	—	624 MB	41.7MMBench	—	—	OpenVLM
2	SmolVLM2-256M	Multimodal	Vision-Language	260.0M	—	624 MB	11.9MMBench	—	—	OpenVLM
3	SmolVLM-500M	Multimodal	Vision-Language	510.0M	—	1.2 GB	53.8MMBench	—	—	OpenVLM
4	SmolVLM2-500M	Multimodal	Vision-Language	510.0M	—	1.2 GB	53.1MMBench	—	—	OpenVLM
5	H2OVL-800M	Multimodal	Vision-Language	830.0M	—	1.9 GB	56.3MMBench	—	—	OpenVLM
6	InternVL3-1B	Multimodal	Vision-Language	940.0M	—	2.2 GB	72.3MMBench	—	—	OpenVLM
7	InternVL2-1B	Multimodal	Vision-Language	1.0B	—	2.3 GB	65.2MMBench	—	—	OpenVLM
8	LLaVA-OneVision-0.5B	Multimodal	Vision-Language	1.0B	—	2.3 GB	61.6MMBench	—	—	OpenVLM
9	LLaVA-OneVision-0.5B (SI)	Multimodal	Vision-Language	1.0B	—	2.3 GB	55.8MMBench	—	—	OpenVLM
10	InternVL2.5-1B	Multimodal	Vision-Language	1.0B	—	2.3 GB	——	—	—	OpenVLM
11	InternVL2.5-1B-MPO	Multimodal	Vision-Language	1.0B	—	2.3 GB	70.1MMBench	—	—	OpenVLM
12	Ovis2-1B	Multimodal	Vision-Language	1.3B	—	3.0 GB	71.6MMBench	—	—	OpenVLM
13	Kosmos2	Multimodal	Vision-Language	1.7B	—	4.0 GB	1.1MMBench	—	—	OpenVLM