ASUS Agent Computer: Can Your Gaming PC run Local AI and LLMs?
Qwen
Qwen
The handiness of an AI assistant is what Qwen aims to demonstrate. There are many models available, and this is where you get into the world of tokens. Or, to put it in plain English, the world of massive expense. We won’t pretend we fully understand every buzzword at this end of the price spectrum, as we’re not coders and we haven’t got the kind of budget necessary to play around. Thankfully we know someone who does. In case you think we’re being dim, we’ll paste in the blurb from the Qwen site.
Qwen3.8-Omni-Flash supports a 1M-token context window while maintaining text performance comparable to a text-only model of the same size and delivering significant improvements in omnimodal capabilities. Its core objective is to strengthen agent capabilities in real-world productivity scenarios, advancing omnimodal models from understanding omnimodal content to planning tasks, calling tools, and completing creative work.
Hopefully that’s cleared that up. We’ve got five different sized models to test. Clearly the moment you get near to the memory limits, everything grinds to a halt. This is the perfect use case for the R9700 AI PRO. With 32GB of VRAM it keeps on trucking long after everything else has, basically even if not technically, stopped.


