Qwen3.8-Flash-Next on a 64 GB M2 Ultra: A 66-Minute Real Work Run | Hacker News - But Better

Qwen3.8-Flash-Next on a 64 GB M2 Ultra: A 66-Minute Real Work Run b1tank.github.io

A 66-minute local Pi coding session on a 64 GB M2 Ultra: 106 tool calls, a 131K context window, automatic compaction, and a working macOS OTelux install.

1 points•b1tank•9 days ago•0 comments•

#ultra #flash #qwen3 #real #flash next #minute real #real work #work run

0 comments

No comments yet.

Related stories

Halogen – Fastest Way to Run Qwen3.8-Flash-Next on AMD Strix Halogithub.com
Hacker News · 1 points · about 8 hours ago
Qwen3.8-Flash-Next Is on TensorFold with Speed Boostsx.com
Hacker News · 1 points · 1 day ago
Gemini 3.8 Flash and Flash Cyber vs Muse Spark 1.3: what they costdev.to
DEV Community · 1 points · 3 days ago
Review: Apple's hyper-pricey M5 Ultra Mac Studio made me into a vibe coderarstechnica.com
Ars Technica · 0 points · 7 days ago
Apple Watch Series 12 and Ultra 4 May Have Hidden Flash Storagemacrumors.com
Hacker News · 4 points · 9 days ago
Dreame’s step-climbing X50 Ultra mopping vacuum is hundreds offtheverge.com
The Verge · 0 points · 2 days ago