context.vn

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 TasksImage 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≤500MAll
Max VRAM≤512MB≤1GB≤2GB≤4GB≤8GBAll
Score
RawContext (0-100)
Percentile rank within each task — comparable across domains
Showing 49 models
#ModelDomainTaskParams ↑GFLOPsVRAMContextSpeedArchSource
1
SmolVLM2-500M-Video-Instruct
VideoVideo Understanding507.0M—1.2 GB
6
——Video VLM
2
SmolVLM2-2.2B-Instruct
VideoVideo Understanding2.3B—5.3 GB
31
——Video VLM
3
Phi-3.5-Vision
VideoVideo Understanding4.2B—9.7 GB
36
——Video VLM
4
Phi-4-multimodal-instruct
VideoVideo Understanding5.6B—13.1 GB
19
——Video VLM
5
MovieLLM
VideoVideo Understanding7.0B—16.4 GB———Video VLM
6
Chat-UniVi-7B-v1.5
VideoVideo Understanding7.0B—16.4 GB
11
——Video VLM
7
LLaMA-VID-7B
VideoVideo Understanding7.0B—16.4 GB
8
——Video VLM
8
Video-ChatGPT
VideoVideo Understanding7.0B—16.4 GB
3
——Video VLM
9
VideoChat2-HD
VideoVideo Understanding7.0B—16.4 GB
53
——Video VLM
10
Video-LLaVA
VideoVideo Understanding7.5B—17.6 GB
17
——Video VLM
11
InternVL3-8B
VideoVideo Understanding7.9B—18.6 GB
92
——Video VLM
12
Qwen2-VL-7B
VideoVideo Understanding8.0B—18.8 GB
69
——Video VLM
13
LLaVA-Video-7B-Qwen2
VideoVideo Understanding8.0B—18.8 GB
56
——Video VLM
14
mPLUG-Owl3
VideoVideo Understanding8.1B—18.9 GB
25
——Video VLM
15
InternVL2-8B
VideoVideo Understanding8.1B—18.9 GB
67
——Video VLM
16
InternVL2_5-8B
VideoVideo Understanding8.1B—18.9 GB
86
——Video VLM
17
MiniCPM-V-2.6
VideoVideo Understanding8.1B—19.0 GB
22
——Video VLM
18
MiniGPT4-Video
VideoVideo Understanding8.3B—19.4 GB———Video VLM
19
Qwen2.5-VL-7B
VideoVideo Understanding8.3B—19.4 GB
72
——Video VLM
20
VideoStreaming
VideoVideo Understanding8.3B—19.5 GB———Video VLM
21
MiMo-VL-7B-RL
VideoVideo Understanding8.3B—19.5 GB
64
——Video VLM
22
ShareGPT4Video-8B
VideoVideo Understanding8.3B—19.6 GB———Video VLM
23
Idefics3-8B-Llama3
VideoVideo Understanding8.5B—19.8 GB
28
——Video VLM
24
MiniCPM-o-2_6
VideoVideo Understanding8.7B—20.3 GB
33
——Video VLM
25
Qwen2.5-Omni-7B
VideoVideo Understanding10.7B—25.1 GB
78
——Video VLM
26
VILA1.5-13B
VideoVideo Understanding13.0B—30.5 GB———Video VLM
27
Long-VITA-16K
VideoVideo Understanding14.0B—32.8 GB
58
——Video VLM
28
Aria
VideoVideo Understanding25.3B—59.3 GB
75
——Video VLM
29
Aria
VideoVideo Understanding25.3B—59.3 GB———Video VLM
30
Aria
VideoVideo Understanding25.3B—59.3 GB———Video VLM
31
InternVL2-26B
VideoVideo Understanding25.5B—59.8 GB———Video VLM
32
LLaVA-NeXT-Video-34B
VideoVideo Understanding34.8B—81.6 GB———Video VLM
33
PLLaVA-34B
VideoVideo Understanding34.9B—81.8 GB
44
——Video VLM
34
InternVL3-38B
VideoVideo Understanding38.4B—90.0 GB
97
——Video VLM
35
VILA1.5-40B
VideoVideo Understanding40.0B—93.8 GB
14
——Video VLM
36
LLaVA-OneVision-72B-sft
VideoVideo Understanding73.2B—171.6 GB
50
——Video VLM
37
LLaVA-Video-72B-Qwen2
VideoVideo Understanding73.2B—171.6 GB
61
——Video VLM
38
Qwen2-VL-72B
VideoVideo Understanding73.4B—172.0 GB
83
——Video VLM
39
Qwen2.5-VL-72B
VideoVideo Understanding73.4B—172.0 GB
89
——Video VLM
40
InternVL2-76B
VideoVideo Understanding76.3B—178.8 GB
81
——Video VLM
41
InternVL2_5-78B
VideoVideo Understanding78.4B—183.8 GB
94
——Video VLM
42
InternVL3-78B
VideoVideo Understanding78.4B—183.8 GB
100
——Video VLM
43
Gemini-1.5-Flash
VideoVideo Understanding———
39
——Video VLM
44
Gemini-1.5-Pro
VideoVideo Understanding——————Video VLM
45
Gemini-1.5-Pro
VideoVideo Understanding——————Video VLM
46
GPT-4o-2024-08-06
VideoVideo Understanding———
42
——Video VLM
47
GPT-4o-2024-08-06
VideoVideo Understanding——————Video VLM
48
Claude-3.5-Sonnet
VideoVideo Understanding———
0
——Video VLM
49
Gemini-2.0-Flash
VideoVideo Understanding———
47
——Video VLM