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 51 models

#	Model	Domain	Task	Params ↑	GFLOPs	VRAM	Context	Speed	Arch	Source
1	SmolVLM-256M	Multimodal	Vision-Language	260.0M	—	624 MB	5	—	—	OpenVLM
2	SmolVLM2-256M	Multimodal	Vision-Language	260.0M	—	624 MB	1	—	—	OpenVLM
3	SmolVLM-500M	Multimodal	Vision-Language	510.0M	—	1.2 GB	8	—	—	OpenVLM
4	SmolVLM2-500M	Multimodal	Vision-Language	510.0M	—	1.2 GB	7	—	—	OpenVLM
5	H2OVL-800M	Multimodal	Vision-Language	830.0M	—	1.9 GB	10	—	—	OpenVLM
6	InternVL3-1B	Multimodal	Vision-Language	940.0M	—	2.2 GB	37	—	—	OpenVLM
7	InternVL2-1B	Multimodal	Vision-Language	1.0B	—	2.3 GB	17	—	—	OpenVLM
8	LLaVA-OneVision-0.5B	Multimodal	Vision-Language	1.0B	—	2.3 GB	12	—	—	OpenVLM
9	LLaVA-OneVision-0.5B (SI)	Multimodal	Vision-Language	1.0B	—	2.3 GB	9	—	—	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	30	—	—	OpenVLM
12	Ovis2-1B	Multimodal	Vision-Language	1.3B	—	3.0 GB	34	—	—	OpenVLM
13	Kosmos2	Multimodal	Vision-Language	1.7B	—	4.0 GB	0	—	—	OpenVLM
14	Moondream1	Multimodal	Vision-Language	1.9B	—	4.5 GB	13	—	—	OpenVLM
15	Moondream2	Multimodal	Vision-Language	1.9B	—	4.5 GB	30	—	—	OpenVLM
16	InternLM-XComposer2-1.8B	Multimodal	Vision-Language	2.0B	—	4.7 GB	39	—	—	OpenVLM
17	DeepSeek-VL-1.3B	Multimodal	Vision-Language	2.0B	—	4.7 GB	20	—	—	OpenVLM
18	Mini-InternVL-Chat-2B-V1.5	Multimodal	Vision-Language	2.0B	—	4.7 GB	32	—	—	OpenVLM
19	InternVL2-2B	Multimodal	Vision-Language	2.0B	—	4.7 GB	40	—	—	OpenVLM
20	Qwen2-VL-2B	Multimodal	Vision-Language	2.0B	—	4.7 GB	46	—	—	OpenVLM
21	XinYuan-VL-2B-Instruct	Multimodal	Vision-Language	2.0B	—	4.7 GB	57	—	—	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	45	—	—	OpenVLM
24	InternVL3-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	68	—	—	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	7	—	—	OpenVLM
27	SAIL-VL-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	59	—	—	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	37	—	—	OpenVLM
30	Aquila-VL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	60	—	—	OpenVLM
31	H2OVL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	36	—	—	OpenVLM
32	QTuneVL1-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	—	—	—	OpenVLM
33	SmolVLM2	Multimodal	Vision-Language	2.3B	—	5.3 GB	33	—	—	OpenVLM
34	SmolVLM-Instruct	Multimodal	Vision-Language	2.3B	—	5.4 GB	22	—	—	OpenVLM
35	SmolVLM-Instruct-DPO	Multimodal	Vision-Language	2.3B	—	5.4 GB	17	—	—	OpenVLM
36	SmolVLM-Synthetic	Multimodal	Vision-Language	2.3B	—	5.4 GB	8	—	—	OpenVLM
37	HawkVL-2B	Multimodal	Vision-Language	2.4B	—	5.7 GB	—	—	—	OpenVLM
38	Ovis2-2B	Multimodal	Vision-Language	2.5B	—	5.8 GB	58	—	—	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	27	—	—	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	55	—	—	OpenVLM
45	granite-vision-3.3-2b	Multimodal	Vision-Language	3.0B	—	7.0 GB	41	—	—	OpenVLM
46	PaliGemma-3B-mix-448	Multimodal	Vision-Language	3.0B	—	7.0 GB	33	—	—	OpenVLM
47	MiniCPM-V	Multimodal	Vision-Language	3.0B	—	7.0 GB	15	—	—	OpenVLM
48	VILA1.5-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	16	—	—	OpenVLM
49	BlueLM-V-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	87	—	—	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	46	—	—	OpenVLM