TextGen (Text Generation Web UI)

What is TextGen (Text Generation Web UI)?

TextGen, previously known as Text Generation Web UI, is an open-source application for running large language models on your own computer with no telemetry. You can download a portable build for Linux, Windows or macOS, unzip it and double-click to open a window, or run the web interface in a browser through a one-click installer, a Conda setup or Docker. It loads GGUF models through llama.cpp and also supports ik_llama.cpp, Transformers, ExLlamaV3 and TensorRT-LLM backends, and you can switch models without restarting. The interface offers instruct and character chat modes, image attachments for vision models, uploads of text, PDF and docx files, message editing with branching, and a notebook tab for free-form generation. A built-in API follows OpenAI and Anthropic formats with tool calling, and MCP servers are supported. It can also fine-tune LoRAs and generate images with diffusers models. The project is free and AGPL-3.0 licensed; your only cost is the hardware you run it on.

Use cases

• Run open LLMs privately on your own machine
• Chat with documents and images offline
• Serve a local OpenAI-compatible API
• Fine-tune LoRAs on chat datasets
• Call tools and MCP servers from local models
• Generate images with diffusers models

Who it's for

• Developers
• AI hobbyists
• Researchers
• Privacy-conscious users

Why use TextGen (Text Generation Web UI)

• Everything runs offline with zero telemetry, so prompts and files stay on your machine.
• It is free and open source, with no subscription or per-token fee.
• A drop-in OpenAI/Anthropic-style API lets existing apps point at a local model.
• Several backends and quantization formats let you match the runtime to your hardware.
• Training, vision, tools and image generation sit in one interface rather than separate programs.

TextGen (Text Generation Web UI) features

• Portable desktop builds for Linux, Windows and macOS
• GGUF support via llama.cpp plus Transformers, ExLlamaV3 and TensorRT-LLM backends
• OpenAI- and Anthropic-compatible API with tool calling
• MCP server support and one-file Python tools
• Instruct, chat-instruct and chat modes with Jinja2 templates
• Vision input for image attachments
• PDF, text and docx file attachments
• LoRA fine-tuning with resumable runs
• Image generation tab for diffusers models
• Extensions for TTS, voice input and translation

TextGen (Text Generation Web UI) integrations

• llama.cpp
• Hugging Face
• ExLlamaV3
• TensorRT-LLM
• MCP
• Docker

How to get started with TextGen (Text Generation Web UI)

1. Download a portable build from the releases page, or clone the repository and run the start script for your operating system.
2. Choose your GPU vendor if prompted, then open the app window or http://127.0.0.1:7860.
3. Download a GGUF model from Hugging Face and place it in the user_data/models folder.
4. Select the model, pick instruct or chat mode, and start prompting.
5. Add the --api flag to expose the OpenAI-compatible endpoint to other tools.

TextGen (Text Generation Web UI) limitations

• The portable build supports GGUF models only; other backends need the full installation
• The full installation needs about 10 GB of disk space and downloads PyTorch
• Model quality and speed depend on your own GPU, memory and chosen model
• Supported GPU setups include CUDA, Vulkan, ROCm and CPU-only builds, so you pick the right one

TextGen (Text Generation Web UI) pricing

TextGen (Text Generation Web UI) is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

TextGen (Text Generation Web UI) alternatives

The main TextGen (Text Generation Web UI) alternatives listed on Debuly are Ollama, LM Studio, GPT4All, Jan, AnythingLLM and llama.cpp. The table compares pricing and platforms; order is A–Z.

1. 

   AnythingLLM

   Open-source AI app for chatting with your documents and running agents, on desktop, in Docker or as a hosted team workspace.

   Chat assistantsAutomation and agentsDeveloper platforms
   Open sourceVisit AnythingLLM (official site)
2. 

   GPT4All

   Free, open source desktop app and Python client for running language models offline and privately on your own computer.

   Chat assistantsDeveloper platforms
   Open sourceVisit GPT4All (official site)
3. 

   Jan

   Free, open-source desktop AI assistant that runs models offline on your computer or connects to cloud models with your own keys.

   Chat assistantsDeveloper platforms
   Open sourceVisit Jan (official site)
4. 

   llama.cpp

   Open-source engine and desktop app for running LLMs locally, with a built-in OpenAI-compatible API server and web chat UI.

   Developer platformsCodingChat assistants
   Open sourceVisit llama.cpp (official site)
5. 

   LM Studio

   Desktop app for running open language models on your own computer, now with the Bionic agent, a local API and optional US-hosted cloud models.

   Chat assistantsDeveloper platformsCodingProductivity
   FreemiumVisit LM Studio (official site)
6. 

   Ollama

   Open-source app and CLI for running open AI models locally on macOS, Windows and Linux, with optional paid cloud models.

   Developer platformsCodingChat assistants
   Open sourceVisit Ollama (official site)

TextGen (Text Generation Web UI) FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: none collected yet, so a monogram is shown.
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.