Run This Ai
EN DE

FastChat

Open-source platform for training, serving, and evaluating large language models — from the makers of Vicuna and Chatbot Arena

★ 39,489 GitHub Apache-2.0 llmservingchatbotvicunaevaluation LLM & Chat

Overview

FastChat is the open-source platform behind Vicuna and Chatbot Arena (lmsys.org), built to train, serve, and evaluate LLMs. It started as a simple chatbot UI and grew into one of the most popular LLM serving frameworks, powering million-user platforms. FastChat supports multiple models simultaneously, provides OpenAI-compatible APIs, and includes tools for benchmarking and evaluation — all in one package.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  fastchat:
    image: localagi/fastchat:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/fastchat:/data

Best VPS for FastChat →

Related tools

NextChat

Cross-platform ChatGPT web UI with multi-model support for Ollama, Claude, Gemini, and more

Lobe Chat

Extensible, open-source ChatGPT alternative with plugins, knowledge base, and multi-LLM support

Open WebUI

User-friendly WebUI for LLMs (Ollama, OpenAI API)

text-generation-webui

Run local LLMs with a powerful web interface — text, vision, tool-calling, and OpenAI-compatible API

Streamlit

Build and share data apps in pure Python — fast

Gradio

Build and share delightful machine learning apps in Python

Guides & articles

How to Deploy FastChat with Docker: Your Own LLM API in 10 Minutes

Step-by-step tutorial to deploy FastChat via Docker — from pulling the image to your first working LLM API. Real performance numbers, troubleshooting, and hard-earned tips included.

Jun 30, 2026

FastChat: I Spent a Weekend Trying to Host My Own ChatGPT Clone — Here Is What Worked

After trying vLLM, llama.cpp, and every serving framework in between, FastChat was the one that actually worked. Here is my honest experience with multi-model serving, evaluation, and deployment.

Jun 30, 2026