// local-llm · nomic-ai/gpt4all

GPT4All

GPT4All est un projet de LLM locaux open source, créé par nomic-ai (nomic-ai/gpt4all sur GitHub). Il compte 77 360 étoiles sur GitHub et 8 262 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 27 mai 2025.

GPT4All — run local LLMs on any device: a free desktop chat client and Python SDK that run open models entirely on your CPU, no GPU or cloud required

★ 77,4 k étoiles⑂ 8,3 k forksMITmis à jour mai 2025

Voir sur GitHub ↗Official site ↗

▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.

// détails du projet

Détails du projet

Dépôt: nomic-ai/gpt4all
Étoiles GitHub: 77 360
Forks: 8 262
Licence: MIT
Dernière mise à jour sur GitHub: 27 mai 2025
Catégorie: LLM locaux
Type de fiche: Guide d'installation complet
Site officiel: Official site

// fonctionnement

Comment ça marche

Install the desktop app
Download the free installer for Windows, macOS or Linux from nomic.ai/gpt4all.
Download a model
In the app, open the model browser and pick one that fits your RAM — the catalogue shows sizes and requirements; downloads are a few GB each.
Chat — or chat with your documents
Start chatting fully offline, or add a folder under LocalDocs to ask questions about your own files with local retrieval.

// fonctionnalités

Pourquoi on l'adore

Runs on plain CPUs

Quantised GGUF models run usefully on ordinary laptops — no GPU required, which is the whole point.

A real desktop client

Model browser, chat UI and settings in one free app; nothing to configure in a terminal.

LocalDocs

Point it at document folders and chat with their contents using retrieval that never leaves the machine.

SDKs and server mode

Python and Node bindings, plus an OpenAI-style local server, for building on the same models.

// lancez-le

Lancez-le vous-même

Desktop installer
The route most people take — one download, then pick a model in-app.
```
https://nomic.ai/gpt4all
```

Python SDK

From the README: install the bindings and load a model in a few lines.

pip install gpt4all

from gpt4all import GPT4All
model = GPT4All("Meta-Llama-3-8B-Instruct.Q4_0.gguf")
with model.chat_session():
    print(model.generate("How can I run LLMs efficiently on my laptop?", max_tokens=1024))

Local server
The desktop app can serve an OpenAI-compatible API on your machine for other tools to use.
```
Enable "Enable Local Server" in GPT4All settings
```

// cas d'usage

Ce que vous pouvez créer

Private, offline AI chat on a work laptop — nothing leaves the machine
Asking questions over sensitive document folders with LocalDocs
Learning how local models behave before investing in GPU hardware
Embedding a local model in a Python app with the gpt4all package

// faq

Questions fréquentes

Who makes GPT4All?

Nomic AI (nomic-ai/gpt4all on GitHub), the company behind the Atlas data tool.

Is GPT4All free?

Yes — the app, SDKs and ecosystem are MIT licensed and free for commercial use. The models you download carry their own licences — check each one.

Do I need a graphics card?

No. GPT4All is built for CPU inference with quantised models; a GPU speeds things up where supported, but a modern laptop is enough.

How does it compare to a well-known alternative?

Against Ollama, GPT4All gives non-technical users a full graphical app and document chat out of the box, while Ollama is CLI-first and stronger as a developer server. Against LM Studio, the difference is licensing and openness: GPT4All is MIT open source, LM Studio is a polished free-but-closed app.

How do I get started?

Les autres projets de la catégorie LLM locaux avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si GPT4All ne vous convient pas.

Ollama★ 182,1 k
The simplest way to run open language models on your own machine.
Open Webui★ 153,9 k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
llama.cpp★ 130,2 k
LLM inference in C/C++
vLLM★ 93,1 k
A high-throughput and memory-efficient inference and serving engine for LLMs
lobehub★ 83,0 k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

// plus en local-llm

Plus en LLM locaux

Projets de la catégorie LLM locaux proches dans le catalogue, les plus proches en étoiles de GPT4All — continuez à explorer de part et d'autre.

lobehub★ 83,0 k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Unsloth★ 77,2 k
Run and fine-tune LLMs and diffusion models locally — faster training, smaller memory footprint.
vLLM★ 93,1 k
A high-throughput and memory-efficient inference and serving engine for LLMs
litellm★ 60,1 k
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, an…
llama.cpp★ 130,2 k
LLM inference in C/C++
exo★ 47,7 k
Run frontier AI locally.

Obtenir GPT4All

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.

Voir sur GitHub ↗← Plus d'outils LLM locaux