DataLearner logo
MI

MiniCPM-V-2

Multimodal model

MiniCPM-V-2

Release date: 2024-04-10Updated: 2024-04-13Views: 827
Parameters
2.8B
Context length
2K
Multilingual
Supported
Reasoning ability
No data

MiniCPM-V-2 is an AI model published by OpenBMB, released on 2024-04-10, for Multimodal model, with 2.8B parameters, and 2K context length, requiring about 6.87GB storage, with a 37.10 score on MMMU.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

MiniCPM-V-2

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
No data
Release date
2024-04-10
Model file size
6.87GB
MoE architecture
No
Total params / Active params
2.8B / Not applicable
Knowledge cutoff
No data
MiniCPM-V-2

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
N/A
MiniCPM-V-2

Official resources

Paper
N/A
DataLearnerAI blog
N/A
MiniCPM-V-2

API details

API speed
No data
No public API pricing yet.
MiniCPM-V-2

Benchmark Results

MiniCPM-V-2 currently shows benchmark results led by MMMU (73 / 74, score 37.10). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Multimodal Understanding

1 evaluations
Benchmark / mode
Score
Rank/total
MMMU
unknown
37.10
73 / 74
MiniCPM-V-2

Publisher

MiniCPM-V-2

Model Overview

MiniCPM-V-2 is an AI model published by OpenBMB, released on 2024-04-10, for Multimodal model, with 2.8B parameters, and 2K context length, requiring about 6.87GB storage, with a 37.10 score on MMMU.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code