HF's 300MB RL LoRA lifts Qwen3.8-27B to 51% on SWE-bench Pro locally

Hugging Face has released its second harness adapter, Qwen3.8-27B-opencode-adapted: a LoRA trained with reinforcement learning on the frozen Qwen3.8-27B, optimized for the OpenCode coding agent. The adapter is only about 300MB, open-sourced under Apache 2.0, and can run locally via llama.cpp. Community members yb2698 and Disastrous-Work-1632, among others, shared the announcement.

Confirmed

Why it matters

2026-11-18 ~ 2026-11-19 · 5 related posts

Full story(3 episodes)→

Primary sources