AxForge
Sign in Get started

Model reference · open weights

InternVL2_5-MPO

LLMs OpenGVLab Vision + text 4 builds Licence not stated 7k dl/mo

InternVL2_5-MPO is an open-weight language model from OpenGVLab. InternVL2_5-1B-MPO (BF16) weighs 1.9 GB; the smallest configuration that runs it is RTX 3060 12 GB.

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released byOpenGVLab
Released2025-04-18
Parameters2.2B
VRAM1.9 GB for the weights

What it runs on

Memory and cards for InternVL2_5-1B-MPO (BF16)

1.9 GBweights, file size
12 MBcache per 1K tokens
1.9 GBruntime overhead, at least
32,768 tokenscontext max
CardRequests at onceContext maxMemory
8K each32K each
RTX 3060 12 GB7719all 32K11.6 GB
RTX 4060 Ti 16 GB11528all 32K15.4 GB
RTX 3090 24 GB19448all 32K23.4 GB
RTX 4090 24 GB19448all 32K23.4 GB
RTX 5090 32 GB27067all 32K31.0 GB
L40S 48 GB39899all 32K44.0 GB
A100 80 GB738184all 32K78.2 GB
H100 80 GB698174all 32K78.1 GB
RTX PRO 6000 Blackwell 96 GB854213all 32K93.8 GB
DGX Spark (GB10) 128 GB unified988247all 32K107 GB
H200 141 GB1000+323all 32K138 GB
B200 180 GB1000+417all 32K176 GB
Memory needed at each load
Requests at once8K tokens each32K tokens each
13.9 GB4.2 GB
54.3 GB5.8 GB
84.6 GB7.0 GB
165.4 GB10.2 GB
327.0 GB16.7 GB
6410.2 GB29.6 GB

One card, with vLLM's small-card settings.

Builds

Sizes, precisions & builds

BuildParamsPrecisionWeightsSmallest setup
InternVL2_5-2B-MPO-hf ↗ 2.2BBF16 4.4 GBRTX 3060 12 GB
InternVL2_5-1B-MPO (above) ↗ 938MBF16 1.9 GBRTX 3060 12 GB
InternVL2_5-4B-MPO ↗ 3.7BBF16 7.4 GBRTX 3060 12 GB
InternVL2_5-8B-MPO-hf ↗ 8.1BBF16 16.2 GB2× RTX 3060 12 GB

From the model card

What OpenGVLab says about InternVL2_5-MPO

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Read the full model card

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters
  • Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms