Deploy Text Generation Web UI in one click installation.
Feature-rich web interface for running local LLMs with GGUF, GPTQ, and AWQ support on CPU or GPU.
What you can build with Text Generation Web UI
Text Generation Web UI is an open-source Gradio-based interface for loading, running, and interacting with large language models locally. It supports more model formats than virtually any other self-hosted LLM frontend — including GGUF via llama.cpp, GPTQ, AWQ, EXL2, and Transformers — making it the primary tool for users who work with diverse model files from HuggingFace and need full control over inference parameters.
This deployment uses the CPU-optimized build, which runs GGUF-quantized models via the llama.cpp backend — practical on any VPS without a dedicated GPU. Place any GGUF model file into the models volume and it will appear in the Models tab ready to load. Self-hosting keeps your conversations, system prompts, and any documents you share with the model on your own infrastructure.
Key features of Text Generation Web UI
Multi-format model support
Load GGUF, GPTQ, AWQ, EXL2, and Transformers models from the same interface without reconfiguring backends or rebuilding the container.
Chat, instruct, and notebook
Three distinct interaction modes cover multi-turn conversations, structured prompt-response tasks, and freeform text generation in one tool.
Character and persona system
Define detailed AI character cards with backstories, example dialogues, and avatars to shape model behavior across sessions.
OpenAI-compatible API
Enable the optional REST API on port 5000 to connect external applications using standard OpenAI client libraries without code changes.
Extension ecosystem
Community extensions add capabilities like long-term memory, voice input/output, Stable Diffusion integration, and custom tools.
GPU-free CPU inference
Runs GGUF-quantized models on CPU via llama.cpp — a 3-7B parameter model is practical on a standard VPS with 8 GB of RAM.
Why run Text Generation Web UI on Hostinger
Launch in one click
Get your application up and running instantly with a preconfigured setup. No manual installation or complex setup steps.
Security you can rely on
Keep your applications protected with a built-in firewall, DDoS protection, and continuous monitoring.
Built in Docker manager
Run and manage multiple Docker containers from one place. Deploy, update, and monitor your projects with ease.
Launch in one click
Get your application up and running instantly with a preconfigured setup. No manual installation or complex setup steps.
Security you can rely on
Keep your applications protected with a built-in firewall, DDoS protection, and continuous monitoring.
Built in Docker manager
Run and manage multiple Docker containers from one place. Deploy, update, and monitor your projects with ease.