FRAMEWIREIndonesiaUpdated Sep 24Live wire
0:00 / 0:00

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:

Jose RomeroSep 24
0:00 / 0:00

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.

VladSep 242
0:00 / 0:00

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.

BjornSep 24
0:00 / 0:00

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

WbackdownSep 241