1
Performance per dollar is getting faster and cheaper
How we served GLM5.2 on AMD MI355X at 2626 tok/s/node and 213 tok/s single stream at over 2x lower cost than Blackwell.
Wafer Blog
The fastest inference for open models.
- Popular posts
- 2
- Total points
- 578
- HN comments
- 249
- Rank
- #2,368 company
Visit wafer.ai → On Hacker News Jul 2026 – Aug 2026
2
Running Kimi K3 on MI355X at Better Performance per Dollar Than B300
Running Kimi K3 at ~952 tok/s/node, AMD continues to prove its case as the winner in performance per dollar.