This was made with a ROCmFP3 version of Qwen 3.8 27B on Strix Halo.
All made by talking to the Strix Framework Desktop remotely while I am at dinner. Now working on mobile touch controls.
Me watching everyone on the timeline enjoy Qwen 3.8 27B on their local machine
GPT 5.6 sol xhigh vs Kimi K3 vs Qwen 3.8 max preview vs Grok 4.5 high
Qwen 3.8 max isn’t just good at AI tasks.
It’s built to run entire business workflows. And the biggest advantage isn’t the 2.4T parameter headline… It’s what happens when you plug it into an Agent OS. Why Qwen 3.8 Max stands out: → 2.4 trillion parameter Mixture-of-Experts
You have reached the end of the archive
All of qwen38