Hacker News .hnnew | past | comments | ask | show | jobs | submitlogin

You could try getting a DGX Thor devkit with 128GB unified memory. Cheaper than the 96GB mac studio and more FLOPs.


Yeah but slower memory compared to the M3 Ultra. There's a big difference in memory bandwidth, which seems to be a driving factor for inferencing. Training on the other hand, it's probably a lot faster.




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: