News for hackers. Stuff that matters.
Re:Tinybox- offline AI device 120B parameters by ejpir on Saturday March 21, 2026 @06:01PM (#47471934)
unfortunately the bigger models are pretty slow in token speed. The memory is just not that fast.

You can check what each model does on AMD Strix halo here:

https://kyuz0.github.io/amd-strix-halo-toolboxes/

There are no comments on this comment yet.