# GPT4All

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Repository: https://github.com/nomic-ai/gpt4all
Canonical: https://ross.abutalabs.com/products/gpt4all
Homepage: https://nomic.ai/gpt4all
Language: C++
License: MIT
License Family: permissive
Topics: llm-inference, ai-chat
Last push: 2025-05-27T20:05:19+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 23, release rhythm 40, longevity 89
- inputs: {"age_days": 1255, "days_push": 463, "days_rel": 555, "gap_med": 3.5, "n_releases_24m": 15}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 77397, forks 8296 (observed 2026-08-28T04:12:21.632612+00:00)

## What it is
GPT4All is an open-source desktop application that lets users run large language models locally on everyday hardware without GPUs or API calls. It includes a chat interface, installers for Windows/macOS/Linux, and Python bindings built around llama.cpp.

## Use cases
- run chatgpt-like models offline on my laptop
- chat with local llm without sending data to the cloud
- run an llm on cpu without a gpu
- private local ai assistant for my desktop
- use llms in a python app locally
- query my documents with a local model

## When to choose
- you need private, offline LLM inference on consumer hardware
- you want a ready-to-use desktop chat app with no setup
- you need permissive MIT licensing for commercial use
- you want simple Python bindings for local models

## When to avoid
- you need maximum throughput or serving many concurrent users
- you require the largest frontier models that exceed local memory
- you need fine-grained server deployment features like an OpenAI-compatible API cluster

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, chat-interface, gui
- domain: large-language-models, artificial-intelligence, desktop-applications, privacy, self-hosted
- platform: windows, cross-platform, python, cpp
- tags: local-llm, offline-ai, llama.cpp, python-bindings, commercial-use, macos, linux, desktop

## Member repositories
- nomic-ai/gpt4all (main) score 42
- nomic-ai/gpt4all-chat (mirror) score 10
- nomic-ai/pygpt4all (sdk) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.632612+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:14:20.509021+00:00, confidence not recorded.
  - readme: https://github.com/nomic-ai/gpt4all (fetched 2026-08-28T04:12:21.632612+00:00, sha 035af62519b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.