How good is Mac Studio M3 Ultra for Trillion param models like DeepSeekv4?
namegulf
·
2026-04-25
·
via Hacker News: Ask HN
 | |
It might run the smaller flash version, but 96gb is not enough for the trillion-parameter model. The M3 Ultra's GPU is a bit on the weak side for large-scale inference, so you'll be waiting on token prefill for most coding/agent workflows. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
