768GB of cheap Intel Optane DIMM memory sticks used to run 1-trillion-parameter LLM on a system with a single GPU — local Kimi K2.5 install achieved roughly 4 tokens per second

https://ift.tt/1WBtbTQ

Submitted May 24, 2026 at 07:35AM by _Dark_Wing https://ift.tt/qzbe35U via TikTokTikk