x.comthreadkage (@0XKageX0) on X
A tweet describing a free setup for running a ~27B open-source Qwen model on Google Colab's free T4 GPU, driven from VS Code. A Cloudflare tunnel with a proxy locks the endpoint behind an API key, and the endpoint is connected to 9router so Claude Code and Claude Cowork on the desktop can use it. It matters as a pointer to a zero-cost way to get Claude Code-style workflows on a self-hosted open model, though the steps are only in an accompanying video and the tweet gives no configuration or quantisation details.
TL;DR Run a Qwen 27B model on free Colab T4, expose it via a Cloudflare tunnel with an API-key proxy, and route it through 9router into Claude Code and Claude Cowork.
Organisations named here
- Cloudflare
- Claude Code
- Qwen
Technologies named here
- Google Colab
- Qwen
- Claude Code
- VS Code
- Cloudflare Tunnel
- 9Router
- Claude Cowork
- Cloudflare
Related in inference
arxiv.orgpaperMinimally Invasive Steering of Language Models
x.comthreadSamuel Zeng (@SamuelZengML) on X
huggingface.coarticle