oobabooga/textgen

Health v2 · maintenance only

Adoption not part of the score

47585 stars · 5983 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

TextGen is an open-source desktop application for running large language models locally with full privacy and no telemetry. It provides a chat UI with vision, file attachments, and tool-calling, plus an OpenAI/Anthropic-compatible API server backed by multiple inference engines like llama.cpp, ExLlamaV3, and Transformers.

Use cases

• run llm locally on my own gpu
• chat with gguf models offline
• local openai api replacement
• talk to pdf documents with a local model
• fine-tune a lora on chat data
• generate images with diffusers locally
• use mcp tools with a local llm
• private chatgpt alternative without telemetry

When to choose

• you want a one-click desktop app for local LLM inference with no setup
• you need an OpenAI/Anthropic-compatible local API for development
• privacy matters and you need fully offline chat with vision and file support
• you want to switch between multiple backends (llama.cpp, ExLlamaV3, Transformers) without restarting

When to avoid

• you need a headless inference server for production clusters rather than a desktop app
• you only want a lightweight CLI or programmatic library without a GUI
• you require multi-user hosted deployment with access control

Facets

application · maturity active

llm-inference chat-interface http-server rag prompt-engineering mcp stable-diffusion llm-training gui large-language-models artificial-intelligence self-hosted privacy developer-tools windows python self-hosted local-llm gguf llama-cpp openai-compatible-api text-generation-webui character-chat lora-finetuning vision-models tool-calling offline-ai linux macos desktop gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="oobabooga/textgen")