Hacker News new | ask | show | jobs
by storus 248 days ago
Wouldn't this restrict memory to 128GB, wasting M3 Ultra potential?
1 comments
alexandercheema 247 days ago
Blog author here. Actually, no. The model can be streamed into the DGX Spark, so we can run prefill of models much larger than 128GB (e.g. DeepSeek R1) on the DGX Spark. This feature is coming to EXO 1.0 which will be open-sourced soonTM.
link
storus 247 days ago
Excellent! Good luck!
link