InternVL3-8B

OpenGVLab/InternVL3-8B

PublisherOpenGVLab

Download access requirementsMirror available

InternVL3是一个先进的多模态大型语言模型系列，旨在提供卓越的整体性能。该模型在多模态感知和推理能力上相比InternVL 2.5有显著提升，并扩展支持工具使用、GUI代理、工业图像分析、3D视觉感知等应用场景。多模态推理与数学：具备复杂推理和数学问题求解能力。OCR、图表与文档理解：能够识别和理解光学字符、图表及各类文档。多图像与现实世界理解：支持同时处理多张图像并理解真实场景。视觉定位：具备精确定位图像中目标区域的能力。多模态多语言理解：支持多种语言的多模态理解任

Vision & LanguageEmbedding & RetrievalText Chat

View all download instructions Mirror repository documentation and license ↗

Model details

模型介绍

中文整理

InternVL3-8B

Model use case

InternVL3是一个先进的多模态大型语言模型系列，旨在提供卓越的整体性能。该模型在多模态感知和推理能力上相比InternVL 2.5有显著提升，并扩展支持工具使用、GUI代理、工业图像分析、3D视觉感知等应用场景。

主要能力

多模态推理与数学：具备复杂推理和数学问题求解能力。OCR、图表与文档理解：能够识别和理解光学字符、图表及各类文档。多图像与现实世界理解：支持同时处理多张图像并理解真实场景。视觉定位：具备精确定位图像中目标区域的能力。多模态多语言理解：支持多种语言的多模态理解任务。视频理解：能够分析和理解视频内容。GUI定位：具备图形用户界面元素的定位能力。空间推理：具备理解空间关系的能力。语言能力：得益于原生多模态预训练，整体文本性能优于Qwen2.5系列。

输入输出

输入：支持图像、视频、文本及多模态交织序列。输出：文本响应。

运行要求

依赖transformers库，版本需大于等于4.37.2。支持16位浮点（bf16/fp16）推理模式。支持BNB 8位量化以降低显存需求。支持多GPU分布式推理。

基本用法

模型加载：使用transformers库加载InternVL3-8B模型及相关组件。推理方式：支持流式输出以实现实时交互。多图像处理：将多张图像放入同一列表进行批量处理。批量推理：将多个提示放入列表结构即可实现批量处理。多轮对话：可按照OpenAI格式构造消息，或使用pipeline.chat接口进行多轮对话。部署服务：可通过LMDeploy工具将模型快速部署为RESTful API服务。

限制

模型卡片中未明确说明具体限制条款。

License

本项目采用MIT许可证发布。项目中使用的预训练Qwen2.5组件采用Apache-2.0许可证。

优先采用原作者提供的中文模型卡片；仅有英文说明时由闲社AI翻译整理。重要参数、许可证和商用范围请以原文为准。

你将获得什么

完整仓库方式包含该固定版本中的权重、配置、分词器及说明文件；指定版本方式只下载所选文件或整组分片。多模态模型的投影文件、配置等依赖，请按作者说明配齐。

完整仓库可能包含多个权重格式，因此需要的磁盘空间可能大于单一格式的模型大小。下载文件不等于完成模型部署。

使用前须知

运行环境

运行模型需要的设备、工具与依赖，以原作者说明为准。

授权范围

是否允许商用、修改和分发，请查看模型许可证。

闲社提供资料与镜像下载方法，不代表已运行模型或完成安全审计。下载的代码应先检查，再执行。

Problem with the information or download?

Pinned version · Multiple download options

InternVL3-8B model download

Download the full repository or choose a version or file.

Download tools · More than GGUF

Use the Hugging Face download tool to obtain OpenGVLab/InternVL3-8B. Download Safetensors, GGUF, ONNX, configuration and other repository files. Downloading does not mean the tool can run this model.

Pinned-version file information is being completed. Existing downloads remain available, or load the file manifest below.

Choose a mirror or official source, your operating system and download scope below, then copy the command. Install the download tool first if needed.

Pinned version: 853e3a797a661694b1b8ece0cb72dc2b23e3dac9. Downloads files only; does not start the model.

Choose a download source

已根据访问地区推荐 Hugging Face 官方线路，你可以手动切换。

Choose what to download

Need just one GGUF precision? Load the file manifest and choose a version. Direct file links do not require Python; the command below can download multiple shards together.

Quantization / file

This reads the pinned version's file manifest; no model weights are downloaded.

Choose your operating system

For command-line downloads, follow these steps to get the full repository or selected files. Direct file links do not need these steps.

Open a terminal window

Create and open a folder for the model. In the folder's address bar, enter powershell and press Enter.

If Python is not installed, get it from the official Python website. In the terminal, enter python --version; continue when a version number appears.

First time? Install the download tool

Copy this command, paste it into the terminal, press Enter and wait for installation to finish.

python -m pip install --upgrade huggingface_hub

Already installed? Continue to step 3.

Run the download command

Select the button below, paste into the same terminal and press Enter. The tool downloads all files included in the current command.

Copying does not start a download. Paste and run the command on your device.

Where are the downloaded files?

Open the folder you chose. Look for the models folder. When progress stops and the terminal returns to its prompt without errors, check that all files are present. 'Copied' does not mean 'downloaded'.

No response or an error?

python not found: Install Python and reopen the terminal. On Windows, follow the installer's instructions to enable command-line access.

hf not found: Confirm that step 2 succeeded, then reopen the terminal. If needed, add Python's Scripts folder to your user PATH. Do not repeatedly download scripts.

Network interrupted: Stay in the same folder and run the same command again. The tool checks existing files.

Permission or disk error: Choose a writable folder with enough free space. Do not disable system security protection.

View the full download command

$env:HF_ENDPOINT = "https://huggingface.co"
$env:HF_HUB_DISABLE_IMPLICIT_TOKEN = "1"
$env:HF_HUB_DISABLE_XET = "1"
hf download "OpenGVLab/InternVL3-8B" --revision "853e3a797a661694b1b8ece0cb72dc2b23e3dac9" --local-dir "./models/OpenGVLab--InternVL3-8B"

Files transfer directly from the source you choose, not through Xianshe servers.

The version is pinned. Repeating the same command checks existing files. Change the source manually if it is slow or unavailable.

Public models do not require submitting keys to Xianshe. Restricted models still require the author's authorization. On Linux / macOS, use python3 instead of python when appropriate.