Qwen3.8-27B + Hermes adapter lifts SWE-bench Pro to 43% with 4x fewer tokens

yb2698 · x · 2026-11-19

Hugging Face's nathanhabib1011 shipped day three of the adapter release train: a hermes adapter—a LoRA trained inside the hermes agent—for Qwen3.8-27B with thinking mode off, aimed at NousResearch users.

The adapter is live on Hugging Face (harness-hub/Qwen3.8-27B-hermes-adapted). Pi and opencode users got adapters earlier in the week, and the team teased something big for the final day.

Original post →

More from coding & agent

coding & agent channel →