GPT4All
A local AI chatbot runs GGUF models and private document chat on Windows, macOS and Linux without requiring a GPU or cloud API.
GPT4All is a local AI chatbot for people who want language models and document conversations on their own computer. Model inference and LocalDocs processing run on the device without a cloud connection.
- Local model chat: Run GGUF models, including Mistral and DeepSeek R1 distillations, and customize your assistant without relying on a cloud API.
- Document questions: Use LocalDocs to ask questions about your own material while keeping document processing on your machine.
- Application backend: Access local models through a Python client built around llama.cpp, or serve them through a Docker-based, OpenAI-compatible HTTP API.
- Developer integrations: Connect with LangChain and Weaviate, with OpenLIT available for monitoring.
The desktop app supports Windows, macOS and Linux, plus a separate Windows ARM build for Qualcomm Snapdragon and Microsoft SQ1/SQ2 processors. Linux builds support x86-64 rather than ARM. Apple Silicon M-series processors are recommended for macOS.
A GPU isn't required: supported computers can run inference on the CPU. NVIDIA and AMD GPUs can accelerate inference through Vulkan. The software is open source under the MIT license, which permits commercial use.
Desktop Chat AppsChat With Your DocumentsInference Libraries and BindingsInference Servers and ClustersLocal Model RunnersmacOSWindowsLinuxDockerChatGPT & Claude alternativesAI for a modest PCAI for your MacTalk to your PDFs and notesGGUFllama.cpp backendOpenAI-compatible APIQuantizationRAGWorks offline
