cd /news/ai-research/radixark-ships-daisyrose-27b-a-27b-a… · home › topics › ai-research › article
[ARTICLE · art-173389] src=marktechpost.com ↗ pub= topic=ai-research verified=true sentiment=↑ positive

RadixArk Ships DaisyRose-27B, a 27B Agentic Coding Model Trained With Reinforcement Learning Only

RadixArk released DaisyRose-27B, an Apache 2.0 agentic coding model post-trained from Qwen3.8-27B using reinforcement learning only, which more than doubles Terminal Bench 4.1 pass@1 to 12.0 and runs on a single GPU. The release gives developers a permissively licensed 27B coding model that can be served on one GPU.

key takeaway

DaisyRose-27B, post-trained from Qwen3.8-27B with reinforcement learning only, more than doubles Terminal Bench 4.1 pass@1 to 12.0 and runs on a single GPU under Apache 2.0.

by read1 min views6 publishedNov 20, 2026
── more in #ai-research 4 stories · sorted by recency
── more on @radixark 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/radixark-ships-daisy…] indexed:0 read:1min 2026-11-20 · —