Model reference · open weights

InternVL-2

Available as managed deployment LLMs OpenGVLab Vision + text 1 variants 7k dl/mo

InternVL-2 is an open-weight language model from OpenGVLab. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

MakerOpenGVLab
TypeLanguage models
TaskVision + text
Parameters (lead)40.1B
Runs withtransformers
Based onOpenGVLab/InternViT-6B-448px-V1-2, NousResearch/Nous-Hermes-2-Yi-34B
Released2024-02-11
Popularity7k downloads / month
LicenceOpen weights

About

What InternVL-2 is

[📂 GitHub] [📜 InternVL 1.0] [📜 InternVL 1.5] [📜 Mini-InternVL] [📜 InternVL 2.5]

[🆕 Blog] [🗨️ Chat Demo] [🤗 HF Demo] [🚀 Quick Start] [📖 Documents]

Introduction

We are excited to introduce 🤗 InternVL-Chat-V1-2. Inspired by LLaVA-NeXT-34B, we have also adopted Nous-Hermes-2-Yi-34B as the language model. Below is the pipeline.

From the experimental results, we've observed that a stronger language model (34B) can better leverage the powerful capabilities of our vision foundation model.

For better training reproducibility, we follow the minimalist design and data efficiency similar to LLaVA-NeXT. To reduce training costs, we provide a pre-trained MLP projector and only employ around 1.2 million visual instruction tuning samples for SFT. Our model has a total of 40 billion parameters and can be trained within 1.5 days using 32 A100 GPUs. The code, data, and model have been made publicly available.

Model Details

  • Model Type: multimodal large language model (MLLM)

  • Model Stats:

  • Training Strategy:

    • Pre-training Stage
      • Learnable Component: ViT + MLP
      • Data: Trained on 8192x4800=39.3M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR data.
      • Note: In this stage, we first load the pre-trained weights of InternViT-6B-448px-V1-0 and connect it to Nous-Hermes-2-Yi-34B. After pre-training, the extracted ViT is published as InternViT-6B-448px-V1-2. Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle to reduce 1024 tokens to 256 tokens.
    • Supervised Fine-tuning Stage
      • Learnable Component: ViT + MLP + LLM
      • Data: A simplified, fully open-source dataset, containing approximately 1.2 million samples. You can download it from here.

Performance

* Proprietary Model

nameimage sizeMMMU(val)MMMU(test)MathVista(testmini)MMB(test)MMB−CN(test)MMVPMMEScienceQA(image)POPETextVQA(val)SEEDv1(image)VizWiz(test)GQA(test)
GPT−4V*unknown56.855.749.977.074.438.71409/517--78.071.6--
Gemini Ultra*unknown59.4-53.0------82.3---
Gemini Pro*unknown47.9-45.273.674.340.71497/437--74.670.7--
Qwen−VL−Plus*unknown45.240.843.367.070.7-1681/502--78.965.7--
Qwen−VL−Max*unknown51.446.851.077.675.7----79.5---
LLaVA−NEXT−34B672x67251.144.746.579.379.0-1631/39781.887.769.575.963.867.1
InternVL−Chat−V1-2448x44851.646.247.782.281.256.71687/48983.388.072.575.660.064.0
  • In most benchmarks, InternVL-Chat-V1-2 achieves better performance than LLaVA-NeXT-34B.

Here, we have conducted only a simple performance comparison. For more detailed performance information and additional evaluation metrics, please refer to our performance summary table.

Training Details

Data Preparation

Inspired by LLaVA-NeXT, we adopted a data-efficient SFT strategy to train InternVL-Chat-V1-2, utilizing approximately 1.2M of visual instruction tuning samples in total, all of which are fully open-source. In

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys internvl-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (internvl-2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"internvl-2","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

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