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 51 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
14	Moondream1	Multimodal	Vision-Language	1.9B	—	4.5 GB	62.3MMBench	—	—	OpenVLM
15	Moondream2	Multimodal	Vision-Language	1.9B	—	4.5 GB	70.0MMBench	—	—	OpenVLM
16	InternLM-XComposer2-1.8B	Multimodal	Vision-Language	2.0B	—	4.7 GB	73.0MMBench	—	—	OpenVLM
17	DeepSeek-VL-1.3B	Multimodal	Vision-Language	2.0B	—	4.7 GB	66.4MMBench	—	—	OpenVLM
18	Mini-InternVL-Chat-2B-V1.5	Multimodal	Vision-Language	2.0B	—	4.7 GB	70.7MMBench	—	—	OpenVLM
19	InternVL2-2B	Multimodal	Vision-Language	2.0B	—	4.7 GB	73.4MMBench	—	—	OpenVLM
20	Qwen2-VL-2B	Multimodal	Vision-Language	2.0B	—	4.7 GB	74.6MMBench	—	—	OpenVLM
21	XinYuan-VL-2B-Instruct	Multimodal	Vision-Language	2.0B	—	4.7 GB	78.4MMBench	—	—	OpenVLM
22	InternVL2.5-2B	Multimodal	Vision-Language	2.0B	—	4.7 GB	——	—	—	OpenVLM
23	InternVL2.5-2B-MPO	Multimodal	Vision-Language	2.0B	—	4.7 GB	74.5MMBench	—	—	OpenVLM
24	InternVL3-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	80.8MMBench	—	—	OpenVLM
25	QTuneVL1.5-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	——	—	—	OpenVLM
26	Janus-1.3B	Multimodal	Vision-Language	2.1B	—	4.9 GB	52.0MMBench	—	—	OpenVLM
27	SAIL-VL-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	79.0MMBench	—	—	OpenVLM
28	VARCO-VISION-2.0-1.7B	Multimodal	Vision-Language	2.1B	—	5.0 GB	——	—	—	OpenVLM
29	MiniMonkey	Multimodal	Vision-Language	2.2B	—	5.2 GB	72.4MMBench	—	—	OpenVLM
30	Aquila-VL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	79.0MMBench	—	—	OpenVLM
31	H2OVL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	72.1MMBench	—	—	OpenVLM
32	QTuneVL1-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	——	—	—	OpenVLM
33	SmolVLM2	Multimodal	Vision-Language	2.3B	—	5.3 GB	71.4MMBench	—	—	OpenVLM
34	SmolVLM-Instruct	Multimodal	Vision-Language	2.3B	—	5.4 GB	67.5MMBench	—	—	OpenVLM
35	SmolVLM-Instruct-DPO	Multimodal	Vision-Language	2.3B	—	5.4 GB	65.0MMBench	—	—	OpenVLM
36	SmolVLM-Synthetic	Multimodal	Vision-Language	2.3B	—	5.4 GB	53.7MMBench	—	—	OpenVLM
37	HawkVL-2B	Multimodal	Vision-Language	2.4B	—	5.7 GB	——	—	—	OpenVLM
38	Ovis2-2B	Multimodal	Vision-Language	2.5B	—	5.8 GB	78.6MMBench	—	—	OpenVLM
39	SAIL-VL-1.5-2B	Multimodal	Vision-Language	2.5B	—	5.8 GB	——	—	—	OpenVLM
40	Flash-VL-2B-Dynamic-ISS	Multimodal	Vision-Language	2.5B	—	5.9 GB	——	—	—	OpenVLM
41	MiniCPM-V-2	Multimodal	Vision-Language	2.8B	—	6.6 GB	69.1MMBench	—	—	OpenVLM
42	BlueLM-2.5-3B	Multimodal	Vision-Language	2.9B	—	6.8 GB	——	—	—	OpenVLM
43	granite-vision-3.1-2b-preview	Multimodal	Vision-Language	3.0B	—	7.0 GB	——	—	—	OpenVLM
44	granite-vision-3.2-2b	Multimodal	Vision-Language	3.0B	—	7.0 GB	78.1MMBench	—	—	OpenVLM
45	granite-vision-3.3-2b	Multimodal	Vision-Language	3.0B	—	7.0 GB	73.5MMBench	—	—	OpenVLM
46	PaliGemma-3B-mix-448	Multimodal	Vision-Language	3.0B	—	7.0 GB	71.0MMBench	—	—	OpenVLM
47	MiniCPM-V	Multimodal	Vision-Language	3.0B	—	7.0 GB	64.1MMBench	—	—	OpenVLM
48	VILA1.5-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	64.5MMBench	—	—	OpenVLM
49	BlueLM-V-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	84.1MMBench	—	—	OpenVLM
50	BlueLM-2.6-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	——	—	—	OpenVLM
51	DeepSeek-VL2-Tiny	Multimodal	Vision-Language	3.4B	—	8.0 GB	74.6MMBench	—	—	OpenVLM