Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
1.
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 (tomshardware.com)
2.
When networking doesn't work (news.ycombinator.com)
3.
When Networking Doesn't Work (news.ycombinator.com)
Today's top topics: openai anthropic android authority claude artificial intelligence dario amodei chatgpt iphone 18 pro ai regulation google
View all today's topics →