LaunchDevelopersNovember 17, 2026

Hugging Face releases Qwen3.8-27B LoRA adapter for OpenCode

Read original source →huggingface.co

The ~300 MB LoRA (r=32) was RL-trained on a frozen Qwen3.8-27B inside the OpenCode coding agent, the second harness adapter after the Pi release. It runs locally and ships with GGUF weights.

How this story unfolded

1 day · 1 report · 3 community posts · from Nov 18

  1. Nov 18
  2. Nov 19

More stories today

Open the live feed