Qwen 3.8 Flash-Next resolved 17/18 coding jobs on my Strix Halo PC.
But as context grew, generation fell from about 15 to 8 tok/s across three harnesses. One run per task, so I would check context before blaming the agent. The 18-run data:
New Mac Studio day one: Qwen 3.8 27B, fully local, running on Bionic.
The speed is absolutely CRAZY 🤯 Local AI is no longer a compromise.
Can a local AI model create 3D models in three.js?
I tested it with Qwen 3.8 27b on my laptop! The assignment: make a robot with interchangeable parts, 4 animations and an exploded view.
Opensource Diary - Day 2.
Made with Tesseract by Mirage Model - Qwen 3.8 27b Hardware - Single Nvidia 96 RTX 6000 Workstation Edn Rate my edits... today...yikes
You have reached the end of the archive
All of qwen38