Re:Run a 1T parameter model on a 32gb Mac by streaming tenso...
by dev_tools_lab on Thursday March 26, 2026 @07:21AM
(#47529135)
Thanks for this project.
Prioritizing MoE models and adding an intelligent NVMe cache could improve efficiency, especially on the M4 Max where bandwidth makes usage more realistic.
[ Parent
| on HN ]
There are no comments on this comment yet.