self-hosted local LLM chat
A self-hosted, offline ChatGPT-like chatbot powered by Llama 2 and Code Llama, with an optional OpenAI-compatible API.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it if you need private chat with document/vision support and broader model support (oLLaMa, llama.cpp) under Apache-2.0, at the cost of a more complex setup.
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Choose it if you prefer a polished desktop app over a web server; it runs fully offline and supports many local models, but isn't something you embed in your own server.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
Choose it if you're on macOS and want a native menu-bar app to run GGUF models locally, not a web UI.
A cosy home for your LLMs.
These projects were analysed and named llama-gpt among their alternatives. The relationship is not symmetric — how llama-gpt rates them is a separate judgement, made when llama-gpt is analysed in its own right.
calls llama-gpt “An old, inference-only Llama 2 chat app; choose it only if you specifically need a simple offline Llama-2-era chat.”
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
calls llama-gpt “narrower, self-hosted Llama-only chat UI with minimal features”
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。