Nous releases Hermes adapter for Qwen3.8-27B: +14 points on two agent benchmarks

yb2698 · x · 2026-11-19

Nous Research announced a Hermes LoRA adapter for Alibaba's Qwen3.8-27B, trained with RL inside the Hermes Agent environment for more efficient and accurate agentic development.

The headline: with thinking off it matches the base model at xhigh reasoning while using 3.5–4.4× fewer tokens. Released openly on Hugging Face under apache-2.0.

Related event: NousResearch Releases Hermes Adapter for Qwen3.8-27B, Boosting SWE-Bench Pro to 43.1%(10 posts)→

Original post →

More from coding & agent

coding & agent channel →