Atomic Chat Studio

Chat with open-weight LLMs locally with engines, assistants and local API

Atomic Chat Studio — Chat with open-weight LLMs locally: models, inference engines, providers, assistants and local API.

How to use Atomic Chat Studio

  1. Pick a platform and load a local model in Chat
  2. Send a message and watch streaming with live tok/s speed
  3. Browse Models and switch to another downloaded model
  4. Compare inference engines and activate the right one
  5. Save a cloud provider key or create a custom assistant
  6. Open Local API, copy the curl or python snippet for your app

Features

  • Streaming local chat with tokens-per-second and context meter
  • Model library with sizes, quants and one-click loading
  • Ten inference engines with platform badges and switching
  • Cloud provider key manager with masked keys, all local
  • Custom assistants with per-assistant system prompts
  • Local API tab: live curl and python request builder for :1337
  • Engine recommender that matches models to your platform

Frequently asked questions

Is it free?

Yes, unlimited.

Login to use this free online tool. Create a free account to get started.

Featured on Twelve Tools Hunt for Tools Featured on LaunchBuff Launch Llama Tools Launch your MCP