本地大模型运行MITC++

GPT4All

Private, on-device chat with local document Q&A.

Star 数
77.4K
Fork 数
8.3K
未关闭 Issue
774
最近提交
2025-05-27

数据来自 GitHub API · 更新于 2026-10-15

GPT4All 是什么?

GPT4All by Nomic is a desktop chat app that runs LLMs on everyday CPUs and GPUs. LocalDocs lets you chat with your own files privately.

主要功能

  • Runs on CPU-only laptops
  • LocalDocs for private document chat
  • Python SDK

系统要求

平台
Windows · macOS · Linux
内存
8 GB+
备注
CPU with AVX/AVX2 or Apple Silicon.

如何安装 GPT4All

根据项目 README 整理。开源项目更新很快,请以 GitHub 页面上的最新说明为准。

Desktop app

  1. 1
    Download the installer from nomic.ai/gpt4all and run it.
  2. 2
    Pick a model in the app and start chatting.

Python SDK

  1. 1
    Install and run a model.
    pip install gpt4all
    python -c "from gpt4all import GPT4All; m = GPT4All('Meta-Llama-3-8B-Instruct.Q4_0.gguf'); print(m.generate('Hello'))"

优势

  • Works on modest hardware
  • Document chat built in

不足

  • Slower release cadence than Ollama

GPT4All 替代品对比

软件Star 数许可证平台显存
GPT4All

Private, on-device chat with local document Q&A.

77.4KMIT—
Jan

Open-source ChatGPT-style desktop app that runs 100% offline.

45KAGPL-3.0—
Ollama

Get up and running with large language models locally.

183.2KMIT—
AnythingLLM

All-in-one desktop and Docker app for private document chat and agents.

67.1KMIT—
llama.cpp

LLM inference in C/C++ — the engine behind most local AI apps.

131.2KMIT—
LocalAI

Self-hosted, OpenAI-compatible API for text, images, audio and more.

49.5KMIT—

常见问题

GPT4All 免费吗?

是的——GPT4All 是开源软件,采用 MIT 许可证。商用前请确认软件及模型权重的许可条款。

GPT4All 支持 Windows、Mac 和 Linux 吗?

GPT4All 支持:Windows, macOS, Linux。

运行 GPT4All 需要什么配置?

RAM: 8 GB+

如何安装 GPT4All?

1. Download the installer from nomic.ai/gpt4all and run it. 2. Pick a model in the app and start chatting.

GPT4All 有哪些好的替代品?

常见替代品包括 Jan, Ollama, AnythingLLM, llama.cpp,详见本页对比表。