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

Qwen 3.8 flash next built this 3d octopus invaders game in about 2 hours on my 2x dgx sparks and i didn't even try hard.

The model is soo tasteful you can feel it in responses. here are the data and specs: qwen 3.8 flash next, 180b moe, official fp8 45 tok/s fresh, 35 tok/s

Sudo suSep 2420
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