Mastodon discussion Discussions Oct 24 1 views

So running inference on qwen3.8-flash-next on AMD Strix Halo is having average power consumption of GPU 45W, less than l...

by jan

So running inference on qwen3.8-flash-next on AMD Strix Halo is having average power consumption of GPU 45W, less than light bulb. With measured generation of about 32tok/s (peaking at 48 and low as 22). Not bad at all. #AI

Read Original
AI Hardware

Metadata

Account
jan@social.janantos.com

Related