Plain-AyI
← All projects
Training & fine-tuning

H2O LLM Studio

A point-and-click app for fine-tuning AI language models on your own data, without writing code.

Research-backedNew this week

What it does

H2O LLM Studio lets you fine-tune large language models, meaning you adapt an existing AI model to your own data or task. Its makers say you can do this without coding, using its graphical interface.

It supports modern techniques such as LoRA, a memory-saving training method, and lets you compare runs, chat with your trained model and share it on the Hugging Face Hub.

The README says it needs a Linux (Ubuntu) machine with a recent NVIDIA graphics card. It can also run on a rented cloud machine.

Who it's for

Data scientists and teams who want to customise language models without heavy coding.

Can I use it without coding?

With some setup. The app itself needs no code, but installing it needs a terminal and a GPU computer. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Cloud
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Use an Ubuntu computer with a recent NVIDIA graphics card, or a cloud machine with the ready-made template.
  2. Install H2O LLM Studio following the README's recommended setup.
  3. Open the app, upload your data and start a fine-tuning run.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it