cd /news/large-language-models/new-lora-adapter-lifts-qwen3-8-codin… · home › topics › large-language-models › article
[ARTICLE · art-171888] src=marktechpost.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65%

Hugging Face released Qwen3.8-27B-pi-adapted, an Apache-2.0 LoRA adapter trained with reinforcement learning for the pi coding agent, lifting SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8%. The adapter targets Qwen3.8-27B and is published under a permissive Apache-2.0 license.

recommendation

For coding-agent work on Qwen3.8-27B, apply the Apache-2.0 pi-adapted LoRA adapter rather than the base model; it lifted SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7%.

more in playbook: Working with AI coding agents
by read1 min views3 publishedNov 18, 2026

Hugging Face released Qwen3.8-27B-pi-adapted, an Apache-2.0 LoRA adapter trained with reinforcement learning for the pi coding agent. It lifts SWE-bench Pro hard-51 pass@1 from 39.2% to 64.7% and Terminal-Bench 2.1 from 39.5% to 55.8%.

The post New LoRA Adapter Lifts Qwen3.8 Coding Success From 39% to 65% appeared first on MarkTechPost.

── more in #large-language-models 4 stories · sorted by recency
── more on @hugging face 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/new-lora-adapter-lif…] indexed:0 read:1min 2026-11-18 · —