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 Vision-Language (285)UI Understanding (14)

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 299 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	ShowUI ui-understandingelement-groundinggui-agent	Multimodal	UI Understanding	2.0B	—	4.7 GB	75.1ScreenSpot	—	Qwen2-VL-2B + UI-guided token selection	Curated
25	UI-TARS-2B (ByteDance) ui-understandinggui-agentelement-grounding	Multimodal	UI Understanding	2.0B	—	4.7 GB	83.8ScreenSpot	—	Qwen2-VL-2B fine-tuned	Curated
26	InternVL3-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	80.8MMBench	—	—	OpenVLM
27	QTuneVL1.5-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	——	—	—	OpenVLM
28	Janus-1.3B	Multimodal	Vision-Language	2.1B	—	4.9 GB	52.0MMBench	—	—	OpenVLM
29	SAIL-VL-2B	Multimodal	Vision-Language	2.1B	—	4.9 GB	79.0MMBench	—	—	OpenVLM
30	VARCO-VISION-2.0-1.7B	Multimodal	Vision-Language	2.1B	—	5.0 GB	——	—	—	OpenVLM
31	MiniMonkey	Multimodal	Vision-Language	2.2B	—	5.2 GB	72.4MMBench	—	—	OpenVLM
32	Aquila-VL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	79.0MMBench	—	—	OpenVLM
33	H2OVL-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	72.1MMBench	—	—	OpenVLM
34	QTuneVL1-2B	Multimodal	Vision-Language	2.2B	—	5.2 GB	——	—	—	OpenVLM
35	SmolVLM2	Multimodal	Vision-Language	2.3B	—	5.3 GB	71.4MMBench	—	—	OpenVLM
36	SmolVLM-Instruct	Multimodal	Vision-Language	2.3B	—	5.4 GB	67.5MMBench	—	—	OpenVLM
37	SmolVLM-Instruct-DPO	Multimodal	Vision-Language	2.3B	—	5.4 GB	65.0MMBench	—	—	OpenVLM
38	SmolVLM-Synthetic	Multimodal	Vision-Language	2.3B	—	5.4 GB	53.7MMBench	—	—	OpenVLM
39	HawkVL-2B	Multimodal	Vision-Language	2.4B	—	5.7 GB	——	—	—	OpenVLM
40	Ovis2-2B	Multimodal	Vision-Language	2.5B	—	5.8 GB	78.6MMBench	—	—	OpenVLM
41	SAIL-VL-1.5-2B	Multimodal	Vision-Language	2.5B	—	5.8 GB	——	—	—	OpenVLM
42	Flash-VL-2B-Dynamic-ISS	Multimodal	Vision-Language	2.5B	—	5.9 GB	——	—	—	OpenVLM
43	MiniCPM-V-2	Multimodal	Vision-Language	2.8B	—	6.6 GB	69.1MMBench	—	—	OpenVLM
44	BlueLM-2.5-3B	Multimodal	Vision-Language	2.9B	—	6.8 GB	——	—	—	OpenVLM
45	granite-vision-3.1-2b-preview	Multimodal	Vision-Language	3.0B	—	7.0 GB	——	—	—	OpenVLM
46	granite-vision-3.2-2b	Multimodal	Vision-Language	3.0B	—	7.0 GB	78.1MMBench	—	—	OpenVLM
47	granite-vision-3.3-2b	Multimodal	Vision-Language	3.0B	—	7.0 GB	73.5MMBench	—	—	OpenVLM
48	PaliGemma-3B-mix-448	Multimodal	Vision-Language	3.0B	—	7.0 GB	71.0MMBench	—	—	OpenVLM
49	MiniCPM-V	Multimodal	Vision-Language	3.0B	—	7.0 GB	64.1MMBench	—	—	OpenVLM
50	VILA1.5-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	64.5MMBench	—	—	OpenVLM
51	BlueLM-V-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	84.1MMBench	—	—	OpenVLM
52	BlueLM-2.6-3B	Multimodal	Vision-Language	3.0B	—	7.0 GB	——	—	—	OpenVLM
53	DeepSeek-VL2-Tiny	Multimodal	Vision-Language	3.4B	—	8.0 GB	74.6MMBench	—	—	OpenVLM
54	Ovis-U1-3B	Multimodal	Vision-Language	3.6B	—	8.5 GB	——	—	—	OpenVLM
55	Vintern-3B-beta	Multimodal	Vision-Language	3.7B	—	8.7 GB	70.6MMBench	—	—	OpenVLM
56	Vintern-1B-v2	Multimodal	Vision-Language	3.7B	—	8.7 GB	——	—	—	OpenVLM
57	Qwen2.5-VL-3B	Multimodal	Vision-Language	3.8B	—	8.8 GB	79.1MMBench	—	—	OpenVLM
58	QTuneVL1.5-3B	Multimodal	Vision-Language	3.8B	—	8.8 GB	——	—	—	OpenVLM
59	Ristretto-3B	Multimodal	Vision-Language	3.8B	—	9.0 GB	——	—	—	OpenVLM
60	Mini-InternVL-Chat-4B-V1.5	Multimodal	Vision-Language	4.0B	—	9.4 GB	75.7MMBench	—	—	OpenVLM
61	InternVL2-4B	Multimodal	Vision-Language	4.0B	—	9.4 GB	78.5MMBench	—	—	OpenVLM
62	Phi-3.5-Vision	Multimodal	Vision-Language	4.0B	—	9.4 GB	76.0MMBench	—	—	OpenVLM
63	InternVL2.5-4B	Multimodal	Vision-Language	4.0B	—	9.4 GB	——	—	—	OpenVLM
64	InternVL2.5-4B-MPO	Multimodal	Vision-Language	4.0B	—	9.4 GB	80.4MMBench	—	—	OpenVLM
65	Ovis1.6-Llama3.2-3B	Multimodal	Vision-Language	4.1B	—	9.6 GB	78.5MMBench	—	—	OpenVLM
66	Phi-3-Vision	Multimodal	Vision-Language	4.2B	—	9.8 GB	73.6MMBench	—	—	OpenVLM
67	Gemma3-4B	Multimodal	Vision-Language	4.3B	—	10.1 GB	69.6MMBench	—	—	OpenVLM
68	AKI-4B	Multimodal	Vision-Language	4.3B	—	10.1 GB	68.8MMBench	—	—	OpenVLM
69	XGen-MM-Instruct-Interleave-v1.5	Multimodal	Vision-Language	4.4B	—	10.3 GB	78.3MMBench	—	—	OpenVLM
70	XGen-MM-Instruct-DPO-v1.5	Multimodal	Vision-Language	4.4B	—	10.3 GB	78.0MMBench	—	—	OpenVLM
71	Ovis2-4B	Multimodal	Vision-Language	4.6B	—	10.8 GB	83.6MMBench	—	—	OpenVLM
72	R-4B	Multimodal	Vision-Language	4.8B	—	11.3 GB	——	—	—	OpenVLM
73	ScreenAI (Google) ui-understandingscreenshot-qascreen2words	Multimodal	UI Understanding	5.0B	—	11.7 GB	——	—	PaLI-based VLM	Curated
74	Phi-4-MultiModal	Multimodal	Vision-Language	5.6B	—	13.1 GB	83.4MMBench	—	—	OpenVLM
75	Yi-VL-6B	Multimodal	Vision-Language	6.6B	—	15.5 GB	68.4MMBench	—	—	OpenVLM
76	InternLM-XComposer2	Multimodal	Vision-Language	7.0B	—	16.4 GB	80.7MMBench	—	—	OpenVLM
77	InternLM-XComposer2-4KHD	Multimodal	Vision-Language	7.0B	—	16.4 GB	80.2MMBench	—	—	OpenVLM
78	WeMM	Multimodal	Vision-Language	7.0B	—	16.4 GB	79.3MMBench	—	—	OpenVLM
79	Chameleon-7B	Multimodal	Vision-Language	7.0B	—	16.4 GB	15.4MMBench	—	—	OpenVLM
80	Slime-7B	Multimodal	Vision-Language	7.0B	—	16.4 GB	65.8MMBench	—	—	OpenVLM
81	MUG-U-7B	Multimodal	Vision-Language	7.0B	—	16.4 GB	83.9MMBench	—	—	OpenVLM
82	Ferret-UI (Apple) ui-understandingscreenshot-analysiselement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	87.0ScreenSpot	—	Ferret + any-resolution	Curated
83	Ferret-UI 2 (Apple) ui-understandingscreenshot-analysiselement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	——	—	Ferret-UI + multi-platform	Curated
84	UI-TARS-7B (ByteDance) ui-understandinggui-agentelement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	90.3ScreenSpot	—	Qwen2-VL-7B fine-tuned	Curated
85	UGround (UIX-Qwen2-7B) ui-understandingelement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	82.8ScreenSpot	—	Qwen2-VL-7B fine-tuned	Curated
86	Aguvis-7B ui-understandinggui-agentelement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	——	—	Qwen2-VL-7B fine-tuned	Curated
87	OS-Atlas-Pro-7B ui-understandinggui-agentelement-grounding	Multimodal	UI Understanding	7.0B	—	16.4 GB	84.6ScreenSpot	—	InternVL2-based	Curated
88	LLaVA-Next-Vicuna-7B	Multimodal	Vision-Language	7.1B	—	16.6 GB	69.2MMBench	—	—	OpenVLM
89	LLaVA-v1.5-7B (QLoRA)	Multimodal	Vision-Language	7.2B	—	16.9 GB	67.7MMBench	—	—	OpenVLM
90	ShareGPT4V-7B	Multimodal	Vision-Language	7.2B	—	16.9 GB	67.6MMBench	—	—	OpenVLM
91	LLaVA-v1.5-7B	Multimodal	Vision-Language	7.2B	—	16.9 GB	66.5MMBench	—	—	OpenVLM
92	LLaVA-v1-7B	Multimodal	Vision-Language	7.2B	—	16.9 GB	43.8MMBench	—	—	OpenVLM
93	MolmoE-1B	Multimodal	Vision-Language	7.2B	—	16.9 GB	64.6MMBench	—	—	OpenVLM
94	DeepSeek-VL-7B	Multimodal	Vision-Language	7.3B	—	17.1 GB	73.8MMBench	—	—	OpenVLM
95	Janus-Pro-7B	Multimodal	Vision-Language	7.4B	—	17.4 GB	62.6MMBench	—	—	OpenVLM
96	LLaVA-Next-Mistral-7B	Multimodal	Vision-Language	7.6B	—	17.8 GB	69.6MMBench	—	—	OpenVLM
97	LLaVA-InternLM-7B (QLoRA)	Multimodal	Vision-Language	7.6B	—	17.8 GB	69.0MMBench	—	—	OpenVLM
98	MMAlaya	Multimodal	Vision-Language	7.8B	—	18.3 GB	58.7MMBench	—	—	OpenVLM
99	InternVL3-8B	Multimodal	Vision-Language	7.9B	—	18.6 GB	83.6MMBench	—	—	OpenVLM
100	SAIL-VL-1.5-8B	Multimodal	Vision-Language	8.0B	—	18.6 GB	——	—	—	OpenVLM
101	MiniCPM-Llama3-V2.5	Multimodal	Vision-Language	8.0B	—	18.8 GB	77.6MMBench	—	—	OpenVLM
102	IDEFICS2-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	75.7MMBench	—	—	OpenVLM
103	InternLM-XComposer	Multimodal	Vision-Language	8.0B	—	18.8 GB	74.4MMBench	—	—	OpenVLM
104	LLaVA-LLaMA-3-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	71.7MMBench	—	—	OpenVLM
105	ShareCaptioner	Multimodal	Vision-Language	8.0B	—	18.8 GB	66.5MMBench	—	—	OpenVLM
106	VisualGLM	Multimodal	Vision-Language	8.0B	—	18.8 GB	37.6MMBench	—	—	OpenVLM
107	InstructBLIP-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	33.9MMBench	—	—	OpenVLM
108	MiniGPT-4-v1-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	23.0MMBench	—	—	OpenVLM
109	MiniGPT-4-v2	Multimodal	Vision-Language	8.0B	—	18.8 GB	9.4MMBench	—	—	OpenVLM
110	InternVL2-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	82.0MMBench	—	—	OpenVLM
111	Cambrian-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	74.6MMBench	—	—	OpenVLM
112	InternLM-XComposer2.5	Multimodal	Vision-Language	8.0B	—	18.8 GB	82.0MMBench	—	—	OpenVLM
113	Bunny-Llama3-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	78.3MMBench	—	—	OpenVLM
114	Ovis1.5-Llama3-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	80.8MMBench	—	—	OpenVLM
115	LLaVA-Next-Llama3	Multimodal	Vision-Language	8.0B	—	18.8 GB	74.8MMBench	—	—	OpenVLM
116	LLaVA-Next-Interleave-7B-DPO	Multimodal	Vision-Language	8.0B	—	18.8 GB	73.8MMBench	—	—	OpenVLM
117	LLaVA-Next-Interleave-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	74.7MMBench	—	—	OpenVLM
118	Mantis-8B-clip-llama3	Multimodal	Vision-Language	8.0B	—	18.8 GB	68.2MMBench	—	—	OpenVLM
119	Mantis-8B-siglip-llama3	Multimodal	Vision-Language	8.0B	—	18.8 GB	69.0MMBench	—	—	OpenVLM
120	Mantis-8B-Idefics2	Multimodal	Vision-Language	8.0B	—	18.8 GB	76.0MMBench	—	—	OpenVLM
121	MiniCPM-V-2.6	Multimodal	Vision-Language	8.0B	—	18.8 GB	81.5MMBench	—	—	OpenVLM
122	Llama-3-MixSense-v1.1	Multimodal	Vision-Language	8.0B	—	18.8 GB	77.0MMBench	—	—	OpenVLM
123	Parrot-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	72.0MMBench	—	—	OpenVLM
124	Llama-3-VILA1.5-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	62.1MMBench	—	—	OpenVLM
125	Idefics3-8B-Llama3	Multimodal	Vision-Language	8.0B	—	18.8 GB	77.5MMBench	—	—	OpenVLM
126	Qwen2-VL-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	82.8MMBench	—	—	OpenVLM
127	Mantis-8B-Fuyu	Multimodal	Vision-Language	8.0B	—	18.8 GB	46.6MMBench	—	—	OpenVLM
128	Slime-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	72.8MMBench	—	—	OpenVLM
129	LLaVA-OneVision-7B	Multimodal	Vision-Language	8.0B	—	18.8 GB	83.2MMBench	—	—	OpenVLM
130	LLaVA-OneVision-7B (SI)	Multimodal	Vision-Language	8.0B	—	18.8 GB	80.5MMBench	—	—	OpenVLM
131	Molmo-7B-D	Multimodal	Vision-Language	8.0B	—	18.8 GB	73.6MMBench	—	—	OpenVLM
132	Molmo-7B-O	Multimodal	Vision-Language	8.0B	—	18.8 GB	72.2MMBench	—	—	OpenVLM
133	InternVL2-8B-MPO	Multimodal	Vision-Language	8.0B	—	18.8 GB	79.2MMBench	—	—	OpenVLM
134	InternVL2-8B-MPO-CoT	Multimodal	Vision-Language	8.0B	—	18.8 GB	78.3MMBench	—	—	OpenVLM
135	InternVL2.5-8B	Multimodal	Vision-Language	8.0B	—	18.8 GB	——	—	—	OpenVLM
136	InternVL2.5-8B-MPO	Multimodal	Vision-Language	8.0B	—	18.8 GB	83.9MMBench	—	—	OpenVLM
137	LLaVA-InternLM2-7B (QLoRA)	Multimodal	Vision-Language	8.1B	—	19.0 GB	73.3MMBench	—	—	OpenVLM
138	mPLUG-Owl2	Multimodal	Vision-Language	8.2B	—	19.2 GB	66.0MMBench	—	—	OpenVLM
139	Ross-Qwen2-7B	Multimodal	Vision-Language	8.2B	—	19.2 GB	80.5MMBench	—	—	OpenVLM
140	Qwen2.5-VL-7B	Multimodal	Vision-Language	8.3B	—	19.4 GB	83.2MMBench	—	—	OpenVLM
141	WeThink-Qwen2.5VL-7B	Multimodal	Vision-Language	8.3B	—	19.4 GB	——	—	—	OpenVLM
142	POINTS-Qwen2.5-7B	Multimodal	Vision-Language	8.3B	—	19.5 GB	81.4MMBench	—	—	OpenVLM
143	POINTS1.5-Qwen2.5-7B	Multimodal	Vision-Language	8.3B	—	19.5 GB	82.8MMBench	—	—	OpenVLM
144	VITA-1.5	Multimodal	Vision-Language	8.3B	—	19.5 GB	79.8MMBench	—	—	OpenVLM
145	MiMo-VL-7B	Multimodal	Vision-Language	8.3B	—	19.5 GB	——	—	—	OpenVLM
146	SAIL-VL-1.6-8B	Multimodal	Vision-Language	8.3B	—	19.5 GB	——	—	—	OpenVLM
147	Emu3_chat	Multimodal	Vision-Language	8.5B	—	19.9 GB	63.8MMBench	—	—	OpenVLM
148	MiniCPM-o-2.6	Multimodal	Vision-Language	8.7B	—	20.3 GB	83.4MMBench	—	—	OpenVLM
149	Ola-7b	Multimodal	Vision-Language	8.9B	—	20.8 GB	87.4MMBench	—	—	OpenVLM
150	valley2	Multimodal	Vision-Language	8.9B	—	20.8 GB	——	—	—	OpenVLM
151	valley2_dpo	Multimodal	Vision-Language	8.9B	—	20.8 GB	——	—	—	OpenVLM
152	Valley-Eagle	Multimodal	Vision-Language	8.9B	—	20.9 GB	——	—	—	OpenVLM
153	Ovis2-8B	Multimodal	Vision-Language	8.9B	—	21.0 GB	84.8MMBench	—	—	OpenVLM
154	IDEFICS-9B-Instruct	Multimodal	Vision-Language	9.0B	—	21.1 GB	45.3MMBench	—	—	OpenVLM
155	OpenFlamingo v2	Multimodal	Vision-Language	9.0B	—	21.1 GB	5.7MMBench	—	—	OpenVLM
156	GLM-4v-9B	Multimodal	Vision-Language	9.0B	—	21.1 GB	71.4MMBench	—	—	OpenVLM
157	Eagle-X5-7B	Multimodal	Vision-Language	9.0B	—	21.1 GB	70.1MMBench	—	—	OpenVLM
158	InternVL3-9B	Multimodal	Vision-Language	9.1B	—	21.4 GB	83.9MMBench	—	—	OpenVLM
159	POINTS-Yi-1.5-9B	Multimodal	Vision-Language	9.5B	—	22.3 GB	81.6MMBench	—	—	OpenVLM
160	Qwen-VL-Chat	Multimodal	Vision-Language	9.6B	—	22.5 GB	61.8MMBench	—	—	OpenVLM
161	Qwen-VL	Multimodal	Vision-Language	9.6B	—	22.5 GB	32.2MMBench	—	—	OpenVLM
162	SeeClick ui-understandingelement-groundinggui-agent	Multimodal	UI Understanding	9.6B	—	22.5 GB	73.4ScreenSpot	—	Qwen-VL + GUI grounding	Curated
163	Monkey-Chat	Multimodal	Vision-Language	9.8B	—	23.0 GB	72.4MMBench	—	—	OpenVLM
164	Monkey	Multimodal	Vision-Language	9.8B	—	23.0 GB	59.6MMBench	—	—	OpenVLM
165	Ovis1.6-Gemma2-9B	Multimodal	Vision-Language	10.2B	—	23.9 GB	83.4MMBench	—	—	OpenVLM
166	Llama-3.2-11B-Vision-Instruct	Multimodal	Vision-Language	11.0B	—	25.8 GB	68.0MMBench	—	—	OpenVLM
167	LLaVA-CoT	Multimodal	Vision-Language	11.0B	—	25.8 GB	——	—	—	OpenVLM
168	Ovis1.5-Gemma2-9B	Multimodal	Vision-Language	11.4B	—	26.7 GB	80.9MMBench	—	—	OpenVLM
169	Falcon2-VLM-11B	Multimodal	Vision-Language	11.4B	—	26.7 GB	70.7MMBench	—	—	OpenVLM
170	OmniLMM-12B	Multimodal	Vision-Language	12.0B	—	28.1 GB	71.7MMBench	—	—	OpenVLM
171	Gemma3-12B	Multimodal	Vision-Language	12.2B	—	28.6 GB	77.5MMBench	—	—	OpenVLM
172	XVERSE-V-13B	Multimodal	Vision-Language	13.0B	—	30.5 GB	75.4MMBench	—	—	OpenVLM
173	Cambrian-13B	Multimodal	Vision-Language	13.0B	—	30.5 GB	73.2MMBench	—	—	OpenVLM
174	OmChat-v2.0-13B	Multimodal	Vision-Language	13.0B	—	30.5 GB	82.6MMBench	—	—	OpenVLM
175	VILA1.5-13B	Multimodal	Vision-Language	13.0B	—	30.5 GB	74.4MMBench	—	—	OpenVLM
176	Slime-13B	Multimodal	Vision-Language	13.0B	—	30.5 GB	65.4MMBench	—	—	OpenVLM
177	Pixtral-12B	Multimodal	Vision-Language	13.0B	—	30.5 GB	77.9MMBench	—	—	OpenVLM
178	TransCore-M	Multimodal	Vision-Language	13.4B	—	31.4 GB	82.3MMBench	—	—	OpenVLM
179	LLaVA-Next-Vicuna-13B	Multimodal	Vision-Language	13.4B	—	31.4 GB	70.0MMBench	—	—	OpenVLM
180	ShareGPT4V-13B	Multimodal	Vision-Language	13.4B	—	31.4 GB	69.8MMBench	—	—	OpenVLM
181	LLaVA-v1.5-13B	Multimodal	Vision-Language	13.4B	—	31.4 GB	69.2MMBench	—	—	OpenVLM
182	LLaVA-v1.5-13B (QLoRA)	Multimodal	Vision-Language	13.4B	—	31.4 GB	68.8MMBench	—	—	OpenVLM
183	PandaGPT-13B	Multimodal	Vision-Language	14.0B	—	32.8 GB	42.5MMBench	—	—	OpenVLM
184	Long-VITA-16K	Multimodal	Vision-Language	14.0B	—	32.8 GB	——	—	—	OpenVLM
185	Eagle-X5-13B	Multimodal	Vision-Language	15.0B	—	35.2 GB	72.6MMBench	—	—	OpenVLM
186	InternVL3-14B	Multimodal	Vision-Language	15.1B	—	35.4 GB	85.7MMBench	—	—	OpenVLM
187	VARCO-VISION-14B	Multimodal	Vision-Language	15.2B	—	35.6 GB	85.1MMBench	—	—	OpenVLM
188	VARCO-VISION-2.0-14B	Multimodal	Vision-Language	15.2B	—	35.6 GB	——	—	—	OpenVLM
189	DeepSeek-VL2-Small	Multimodal	Vision-Language	16.1B	—	37.7 GB	82.8MMBench	—	—	OpenVLM
190	Ovis2-16B	Multimodal	Vision-Language	16.2B	—	38.0 GB	87.2MMBench	—	—	OpenVLM
191	Kimi-VL-A3B-Instruct	Multimodal	Vision-Language	16.4B	—	38.4 GB	82.1MMBench	—	—	OpenVLM
192	Kimi-VL-A3B-Thinking	Multimodal	Vision-Language	16.4B	—	38.4 GB	——	—	—	OpenVLM
193	Kimi-VL-A3B-Thinking-2506	Multimodal	Vision-Language	16.4B	—	38.4 GB	——	—	—	OpenVLM
194	CogVLM-17B-Chat	Multimodal	Vision-Language	17.0B	—	39.8 GB	65.8MMBench	—	—	OpenVLM
195	bailingMM-mini	Multimodal	Vision-Language	17.0B	—	39.8 GB	——	—	—	OpenVLM
196	CogAgent ui-understandinggui-agentscreenshot-analysis	Multimodal	UI Understanding	18.0B	—	42.2 GB	——	—	CogVLM + high-res cross-module	Curated
197	CogVLM2-19B-Chat	Multimodal	Vision-Language	19.0B	—	44.5 GB	73.9MMBench	—	—	OpenVLM
198	LLaVA-InternLM2-20B (QLoRA)	Multimodal	Vision-Language	20.2B	—	47.3 GB	75.1MMBench	—	—	OpenVLM
199	BailingMM-Lite-1203	Multimodal	Vision-Language	21.0B	—	49.2 GB	84.0MMBench	—	—	OpenVLM
200	Aria	Multimodal	Vision-Language	25.3B	—	59.3 GB	80.0MMBench	—	—	OpenVLM
201	InternVL-Chat-V1.5	Multimodal	Vision-Language	26.0B	—	60.9 GB	82.3MMBench	—	—	OpenVLM
202	InternVL2-26B	Multimodal	Vision-Language	26.0B	—	60.9 GB	83.4MMBench	—	—	OpenVLM
203	MMAlaya2	Multimodal	Vision-Language	26.0B	—	60.9 GB	82.5MMBench	—	—	OpenVLM
204	InternVL2.5-26B	Multimodal	Vision-Language	26.0B	—	60.9 GB	——	—	—	OpenVLM
205	InternVL2.5-26B-MPO	Multimodal	Vision-Language	26.0B	—	60.9 GB	85.6MMBench	—	—	OpenVLM
206	Gemma3-27B	Multimodal	Vision-Language	27.4B	—	64.2 GB	82.3MMBench	—	—	OpenVLM
207	DeepSeek-VL2	Multimodal	Vision-Language	27.5B	—	64.5 GB	84.1MMBench	—	—	OpenVLM
208	Ovis1.6-Gemma2-27B	Multimodal	Vision-Language	28.9B	—	67.7 GB	84.8MMBench	—	—	OpenVLM
209	Chameleon-30B	Multimodal	Vision-Language	30.0B	—	70.3 GB	32.5MMBench	—	—	OpenVLM
210	KoreaDeep-VLM-OCR-32B	Multimodal	Vision-Language	32.0B	—	75.0 GB	——	—	—	OpenVLM
211	LLaVA-Next-Qwen-32B	Multimodal	Vision-Language	33.0B	—	77.3 GB	79.4MMBench	—	—	OpenVLM
212	Qwen2.5-VL-32B	Multimodal	Vision-Language	33.5B	—	78.5 GB	——	—	—	OpenVLM
213	Cambrian-34B	Multimodal	Vision-Language	34.0B	—	79.7 GB	80.4MMBench	—	—	OpenVLM
214	Yi-VL-34B	Multimodal	Vision-Language	34.6B	—	81.1 GB	72.4MMBench	—	—	OpenVLM
215	LLaVA-Next-Yi-34B	Multimodal	Vision-Language	34.8B	—	81.6 GB	81.1MMBench	—	—	OpenVLM
216	Ovis2-34B	Multimodal	Vision-Language	34.9B	—	81.8 GB	87.6MMBench	—	—	OpenVLM
217	Eagle-X5-34B-Chat	Multimodal	Vision-Language	36.8B	—	86.3 GB	80.0MMBench	—	—	OpenVLM
218	Emu2_chat	Multimodal	Vision-Language	37.0B	—	86.7 GB	63.6MMBench	—	—	OpenVLM
219	InternVL2.5-38B	Multimodal	Vision-Language	38.0B	—	89.1 GB	——	—	—	OpenVLM
220	InternVL2.5-38B-MPO	Multimodal	Vision-Language	38.0B	—	89.1 GB	86.4MMBench	—	—	OpenVLM
221	InternVL3-38B	Multimodal	Vision-Language	38.4B	—	90.0 GB	87.7MMBench	—	—	OpenVLM
222	InternVL2-40B	Multimodal	Vision-Language	40.0B	—	93.8 GB	86.8MMBench	—	—	OpenVLM
223	VILA1.5-40B	Multimodal	Vision-Language	40.0B	—	93.8 GB	81.7MMBench	—	—	OpenVLM
224	VITA	Multimodal	Vision-Language	47.0B	—	110.2 GB	——	—	—	OpenVLM
225	360VL-70B	Multimodal	Vision-Language	70.0B	—	164.1 GB	78.8MMBench	—	—	OpenVLM
226	Qwen-VL-Max-0809	Multimodal	Vision-Language	72.0B	—	168.8 GB	86.8MMBench	—	—	OpenVLM
227	UI-TARS-72B (ByteDance) ui-understandinggui-agentelement-grounding	Multimodal	UI Understanding	72.0B	—	168.8 GB	92.6ScreenSpot	—	Qwen2-VL-72B fine-tuned	Curated
228	LLaVA-OneVision-72B (SI)	Multimodal	Vision-Language	73.0B	—	171.1 GB	——	—	—	OpenVLM
229	LLaVA-OneVision-72B	Multimodal	Vision-Language	73.0B	—	171.1 GB	85.8MMBench	—	—	OpenVLM
230	Molmo-72B	Multimodal	Vision-Language	73.3B	—	171.8 GB	——	—	—	OpenVLM
231	Qwen2-VL-72B	Multimodal	Vision-Language	73.4B	—	172.0 GB	86.9MMBench	—	—	OpenVLM
232	Qwen2.5-VL-72B	Multimodal	Vision-Language	73.4B	—	172.0 GB	88.3MMBench	—	—	OpenVLM
233	InternVL2-Llama3-76B	Multimodal	Vision-Language	76.0B	—	178.1 GB	86.5MMBench	—	—	OpenVLM
234	InternVL2.5-78B	Multimodal	Vision-Language	78.0B	—	182.8 GB	88.2MMBench	—	—	OpenVLM
235	InternVL2.5-78B-MPO	Multimodal	Vision-Language	78.0B	—	182.8 GB	88.4MMBench	—	—	OpenVLM
236	InternVL3-78B	Multimodal	Vision-Language	78.4B	—	183.8 GB	88.8MMBench	—	—	OpenVLM
237	RBDash-v1.5	Multimodal	Vision-Language	79.0B	—	185.2 GB	84.6MMBench	—	—	OpenVLM
238	NVLM-D-72B	Multimodal	Vision-Language	79.4B	—	186.1 GB	80.4MMBench	—	—	OpenVLM
239	IDEFICS-80B-Instruct	Multimodal	Vision-Language	80.0B	—	187.5 GB	54.6MMBench	—	—	OpenVLM
240	BailingMM-Pro-0120	Multimodal	Vision-Language	81.0B	—	189.8 GB	87.1MMBench	—	—	OpenVLM
241	Llama-3.2-90B-Vision-Instruct	Multimodal	Vision-Language	88.6B	—	207.7 GB	80.4MMBench	—	—	OpenVLM
242	GPT-4o (0513, detail-high)	Multimodal	Vision-Language	—	—	—	83.4MMBench	—	—	OpenVLM
243	GPT-4o (0513, detail-low)	Multimodal	Vision-Language	—	—	—	83.3MMBench	—	—	OpenVLM
244	GLM-4v	Multimodal	Vision-Language	—	—	—	81.3MMBench	—	—	OpenVLM
245	GPT-4v (0409, detail-high)	Multimodal	Vision-Language	—	—	—	81.0MMBench	—	—	OpenVLM
246	GPT-4v (0409, detail-low)	Multimodal	Vision-Language	—	—	—	80.8MMBench	—	—	OpenVLM
247	Qwen-VL-Max	Multimodal	Vision-Language	—	—	—	77.6MMBench	—	—	OpenVLM
248	GPT-4v (1106, detail-low)	Multimodal	Vision-Language	—	—	—	77.0MMBench	—	—	OpenVLM
249	RekaFlash	Multimodal	Vision-Language	—	—	—	76.8MMBench	—	—	OpenVLM
250	Gemini-1.0-Pro	Multimodal	Vision-Language	—	—	—	73.6MMBench	—	—	OpenVLM
251	Claude3-Sonnet	Multimodal	Vision-Language	—	—	—	67.8MMBench	—	—	OpenVLM
252	Qwen-VL-Plus	Multimodal	Vision-Language	—	—	—	67.0MMBench	—	—	OpenVLM
253	RekaEdge	Multimodal	Vision-Language	—	—	—	66.4MMBench	—	—	OpenVLM
254	GPT-4v (1106, detail-high)	Multimodal	Vision-Language	—	—	—	65.4MMBench	—	—	OpenVLM
255	Claude3-Opus	Multimodal	Vision-Language	—	—	—	63.3MMBench	—	—	OpenVLM
256	Claude3-Haiku	Multimodal	Vision-Language	—	—	—	60.7MMBench	—	—	OpenVLM
257	Gemini-1.5-Pro	Multimodal	Vision-Language	—	—	—	73.9MMBench	—	—	OpenVLM
258	Claude3.5-Sonnet	Multimodal	Vision-Language	—	—	—	79.7MMBench	—	—	OpenVLM
259	CongRong	Multimodal	Vision-Language	—	—	—	82.8MMBench	—	—	OpenVLM
260	GPT-4o-mini (0718, detail-high)	Multimodal	Vision-Language	—	—	—	77.6MMBench	—	—	OpenVLM
261	Yi-Vision	Multimodal	Vision-Language	—	—	—	78.1MMBench	—	—	OpenVLM
262	GPT-4o (0806, detail-high)	Multimodal	Vision-Language	—	—	—	82.1MMBench	—	—	OpenVLM
263	Step-1.5V	Multimodal	Vision-Language	—	—	—	85.3MMBench	—	—	OpenVLM
264	Gemini-1.5-Flash	Multimodal	Vision-Language	—	—	—	79.4MMBench	—	—	OpenVLM
265	Qwen-VL-Plus-0809	Multimodal	Vision-Language	—	—	—	82.7MMBench	—	—	OpenVLM
266	Claude3.5-Sonnet-20241022	Multimodal	Vision-Language	—	—	—	82.6MMBench	—	—	OpenVLM
267	Taiyi	Multimodal	Vision-Language	—	—	—	86.7MMBench	—	—	OpenVLM
268	JT-VL-Chat-V3.0	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
269	TeleMM	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
270	Gemini-1.5-Pro-002	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
271	Gemini-1.5-Flash-002	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
272	GPT-4o (1120, detail-high)	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
273	GLM-4v-Plus	Multimodal	Vision-Language	—	—	—	81.4MMBench	—	—	OpenVLM
274	Step-1.5V-mini	Multimodal	Vision-Language	—	—	—	18.1MMBench	—	—	OpenVLM
275	abab6.5s	Multimodal	Vision-Language	—	—	—	61.0MMBench	—	—	OpenVLM
276	abab7-preview	Multimodal	Vision-Language	—	—	—	84.5MMBench	—	—	OpenVLM
277	SenseNova	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
278	Gemini-2.0-Flash	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
279	Step-1o	Multimodal	Vision-Language	—	—	—	88.3MMBench	—	—	OpenVLM
280	HunYuan-Standard-Vision	Multimodal	Vision-Language	—	—	—	86.4MMBench	—	—	OpenVLM
281	GLM-4v-Plus-20250111	Multimodal	Vision-Language	—	—	—	88.9MMBench	—	—	OpenVLM
282	Gemini-2.0-Pro	Multimodal	Vision-Language	—	—	—	84.3MMBench	—	—	OpenVLM
283	Claude3.7-Sonnet	Multimodal	Vision-Language	—	—	—	81.4MMBench	—	—	OpenVLM
284	moonshot-v1-8k	Multimodal	Vision-Language	—	—	—	79.3MMBench	—	—	OpenVLM
285	grok-2-vision-1212	Multimodal	Vision-Language	—	—	—	85.3MMBench	—	—	OpenVLM
286	GPT-4.5	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
287	ChatGPT-4o-latest	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
288	Gemini-2.5-Pro	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
289	GPT-4.1-20250414	Multimodal	Vision-Language	—	—	—	86.9MMBench	—	—	OpenVLM
290	GPT-4.1-mini-20250414	Multimodal	Vision-Language	—	—	—	86.9MMBench	—	—	OpenVLM
291	GPT-4.1-nano-20250414	Multimodal	Vision-Language	—	—	—	68.2MMBench	—	—	OpenVLM
292	SenseNova-V6-Pro	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
293	CongRong-v2.0	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
294	GPT-5-20250807	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
295	GPT-5-nano-20250807	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
296	GPT-5-mini-20250807	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
297	SenseNova-V6-5-Pro	Multimodal	Vision-Language	—	—	—	——	—	—	OpenVLM
298	OmniParser (Microsoft) ui-understandingscreenshot-parsingelement-detection	Multimodal	UI Understanding	—	—	—	93.9ScreenSpot	—	Detection + OCR + Icon pipeline	Curated
299	OmniParser V2 (Microsoft) ui-understandingscreenshot-parsingelement-detection	Multimodal	UI Understanding	—	—	—	——	—	Detection + OCR + Icon pipeline v2	Curated