TextGen (text-generation-webui)

What is TextGen (text-generation-webui)?

TextGen, long known as oobabooga's text-generation-webui, runs open models on your own hardware through llama.cpp (GGUF), ExLlamaV3 or Transformers. It offers a chat and notebook UI with file attachments, vision and tool calling, an OpenAI- and Anthropic-compatible API, and a training tab for fine-tuning LoRAs. Portable builds run as a desktop app; the Docker setup serves the web UI for a team on port 7860.

Where it fits in a 10–200 person business

• Try and compare open models on an office GPU box through a browser UI before standardizing on one
• Local OpenAI-compatible endpoint for internal scripts and tools, with no data leaving the network
• Fine-tune a small LoRA on your own documents or chat transcripts

These use cases are our editorial suggestions, not claims made by the project.

Can a business use TextGen (text-generation-webui)? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does TextGen (text-generation-webui) phone home?

Checked against the project's own docs and repository on Oct 30, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does TextGen (text-generation-webui) need?

The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.

GPU: Optional. Docker variants exist for NVIDIA, AMD, Intel Arc (beta) and CPU-only inference; portable builds come in CUDA, Vulkan, ROCm and CPU-only versions.

No official RAM, CPU or disk minimum is published; memory use depends on the model and quantization you load (the project links a GGUF memory calculator).

Source: github.com/oobabooga/textgen/wiki/09-%E2%80%90-Docker

How much does it cost to host TextGen (text-generation-webui) per month?

How to deploy TextGen (text-generation-webui)

Method: Docker Compose (built locally from the repo)

git clone https://github.com/oobabooga/textgen && cd textgen
# CPU only; for NVIDIA use docker/nvidia, AMD docker/amd, Intel docker/intel
ln -s docker/{cpu/Dockerfile,cpu/docker-compose.yml,.dockerignore} .
cp docker/.env.example .env
mkdir -p user_data/logs user_data/cache
# Edit .env (APP_RUNTIME_GID, TORCH_CUDA_ARCH_LIST) and user_data/CMD_FLAGS.txt (e.g. --listen --cpu)
docker compose up --build
# Web UI on http://localhost:7860

From the official instructions: github.com/oobabooga/textgen#docker. Always check the source for the current version before you run it.

Known gotchas when self-hosting TextGen (text-generation-webui)

• The --listen flag makes the web UI reachable from your network, and --share or --public-api create public URLs. Set --gradio-auth for the UI and --api-key for the API before exposing either. source
• There is no pre-built official image; Docker Compose builds the image locally and needs Docker Compose v2.17 or higher (NVIDIA also needs the NVIDIA Container Toolkit). source
• Without a user_data/ directory next to the compose file, models, characters and settings are lost when the container is rebuilt. source
• ExLlamaV3/Transformers loaders, training, image generation and extensions need the full installation; the portable build only runs GGUF models. source

Alternatives in Local model runtimes

• Ollama The simplest way to download and run open-weight LLMs locally behind an API. Compare Ollama vs TextGen (text-generation-webui)
• llama.cpp Lightweight C/C++ engine that runs quantized open models on CPU or GPU, with an OpenAI-compatible server. Compare llama.cpp vs TextGen (text-generation-webui)
• vLLM High-throughput LLM inference server for GPUs with an OpenAI-compatible API. Compare TextGen (text-generation-webui) vs vLLM
• LocalAI OpenAI-compatible API for LLMs, vision, voice and images on any hardware. Compare LocalAI vs TextGen (text-generation-webui)
• Xinference Model-serving platform for LLM, embedding, rerank, speech and image models behind one OpenAI-compatible API. Compare TextGen (text-generation-webui) vs Xinference
• GPUStack GPU cluster manager that deploys vLLM, SGLang and other engines behind an OpenAI-compatible API. Compare GPUStack vs TextGen (text-generation-webui)

Sources

• GitHub repository: github.com/oobabooga/textgen
• Official documentation: github.com/oobabooga/textgen#installation
• License text: github.com/oobabooga/textgen/blob/main/LICENSE
• Hardware requirements, Gotcha 2, Gotcha 3: github.com/oobabooga/textgen/wiki/09-%E2%80%90-Docker
• Deploy instructions: github.com/oobabooga/textgen#docker
• Gotcha 1, Gotcha 4: github.com/oobabooga/textgen#readme
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 30, 2026