Skip to content
NewA calmer, faster ZeroHour

harness-hub releases a Qwen3.8-27B LoRA for the pi agent

Original title: harness-hub/Qwen3.8-27B-pi-adapted — new model trending #29 on Hugging Face

Hugging Face trending modelsby harness-hub ()6 min read2 · 1 read
AI summary · x-ai/grok-4.7Summaries by Vani AI

Authors report Terminal-Bench 2.1 at 55.8% versus 39.5% for the base model, with 62% fewer tool calls.

harness-hub published a LoRA adapter for Qwen/Qwen3.8-27B, trained with reinforcement learning to drive the pi coding agent on software-engineering and terminal tasks. The card reports large gains versus the base model under pi on Terminal-Bench 2.1 and SWE-bench Pro hard 51, plus fewer tool calls. Step 160 was chosen from checkpoint scores during training. A full recipe is promised in a later blog post; GGUF weights and vLLM, transformers and llama.cpp serving notes are included.

Unconfirmed: Benchmark gains are the publisher's paired evaluation, not an independent leaderboard result.

Key facts
  • SWE-bench Pro hard 51 moved from 29.4% to 62.7%, the authors say, with 18 newly solved and 1 lost.
  • Terminal-Bench 2.1 used 86 tasks; the held-out 68 still showed +16.2 points.
  • Runs used one attempt, temperature 0.8, and thinking off.
  • A linked GGUF repo is harness-hub/Qwen3.8-27B-pi-GGUF.
  • The adapter was not trained or evaluated with thinking enabled.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

6 min read at huggingface.co

A LoRA adapter for [Qwen/Qwen3. 8-27B](https://huggingface. co/Qwen/Qwen3.

Hugging Face trending models

By harness-hub · huggingface.co

Read the full article at Hugging Face trending models

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.