Performance per dollar is getting faster and cheaper | Wafer

GLM5.2 on AMD MI355X at 2626 tok/s/node at over 2x lower cost than Blackwell

The fastest open source LLMs for enterprise.
354 points by latchkey 110 days ago www.wafer.ai 135 comments
Summary not yet generated for this article.

Comments (135 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open