textgen

Project Overview

TextGen is an open-source desktop app for local LLMs, supporting text, vision, tool-calling, and web search with both UI and API.

Key Features

• Chat & generation: instruct, chat-instruct, and chat modes; attach images for visual understanding; upload text files, PDFs, and DOCX documents
• Multiple backends: llama.cpp, ik_llama.cpp, Transformers, ExLlamaV3, and TensorRT-LLM; switch backends and models without restarting
• OpenAI/Anthropic-compatible API: Chat, Completions, and Messages endpoints with tool-calling support
• Training & image generation: LoRA fine-tuning; dedicated image generation tab for diffusers models
• 100% offline and private: zero telemetry, external resources, or remote update requests
• Dark/light themes, syntax highlighting, and LaTeX rendering

Target Audience

• Developers and researchers who want to run LLMs locally
• Privacy-conscious users who don't want data uploaded to the cloud
• Users who need text generation, vision understanding, and tool calling

Quick Start

1. Download portable builds from Releases
2. Unzip and double-click textgen to run
3. Available for Linux, Windows, and macOS with CUDA, Vulkan, ROCm, and CPU-only options
4. Compatible with GGUF (llama.cpp) models

Core Advantages

• 100% offline with zero telemetry, complete privacy
• Supports multiple backends and model formats
• OpenAI/Anthropic-compatible API
• Cross-platform (Linux, Windows, macOS)

System Requirements

• OS: Linux, Windows, macOS