Find tools › Open-source projects › Write code faster

kaggle-tpu-lab

Open-source project · by ARahim3

Run large AI models for free on cloud TPUs and connect them to your coding assistant.

Some setup

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Host open-source LLMs for free
  • Connect Claude Code to custom endpoints
  • Run inference on Kaggle TPUs

How to start

  1. Ensure you have a phone-verified Kaggle account with free TPU quota.

  2. Clone the repository to your local machine.

  3. Run python launch.py serve to push the kernel and start the server.

Good to know. Sessions are limited to just under nine hours, after which you must restart the notebook to get a new URL.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-10-06

More detail

Run open models like Qwen and GLM on Kaggle's free TPU v5e-8 and get a public OpenAI- and Anthropic-compatible API endpoint.

Avoid high cloud bills and GPU hardware costs by leveraging free Kaggle TPU hours to self-host large open models for coding agents.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map