News for hackers. Stuff that matters.
Re:Muse Spark Open by TomGarden on Thursday October 15, 2026 @03:30PM (#50109005)
The exciting thing about this is in them optimizing for inference on Macs. This, and optimization for other consumer hardware, is where local AI needs to go
Re:Muse Spark Open by kristianp on Thursday October 15, 2026 @05:24PM (#50110493)
Given the size of Macs (2 or 4 of them) required to run it, they're just paying lip service to that option. Other models, e.g. deepseek flash, are much more practical size. Even that takes a 96 or 128GB ram Mac.
Re:Muse Spark Open by TomGarden on Friday October 16, 2026 @03:09AM (#50115125)
Yeah I'm more excited about the prospect of them explicitly saying it, which hopefully can lead to better places down the line.

I thought DS Flash needed 2bit quant to work on 128GB? I have an m4 max 128 GB and the most reasonable model to run still seems to be qwen's 32B A3B