// INFERENCE RUNTIME

text-generation-webui

Feature-rich browser-based interface for running LLMs locally. Supports many backends and quantization formats, plus extensions for RAG, character personas, TTS and image generation. The most extensible local LLM UI.
Platforms
Windows, macOS, Linux
Backends
CUDA, ROCm, Metal (via llama.cpp), CPU
Quant formats
GGUF, GPTQ, EXL2, AWQ, HF Transformers (BF16/FP16)
text-generation-webui website โ†—

Videos about text-generation-webui

How to Install TextGen WebUI - Install ANY LLMs IN Minutes Locally! (Oobabooga)

The ULTIMATE Local AI Interface: Text Generation WebUI (Oobabooga) MAX Customization EXPLAINED

How-To Install Text-Generation-WebUI on Windows, Linux, Mac: Updated and Latest Tutorial

FAQ

What platforms does text-generation-webui support?โ–ถ

text-generation-webui runs on Windows, macOS, Linux with backends CUDA, ROCm, Metal (via llama.cpp), CPU.

What quant formats does text-generation-webui support?โ–ถ

text-generation-webui supports GGUF, GPTQ, EXL2, AWQ, HF Transformers (BF16/FP16).