HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by anthonix1 | Hacker News Reader
Parent
Full thread
anthonix1
·
... which also has a much lower power cap
View on HN
skirmish
·
Not that much lower, 295W vs 355W, and for LLM inference VRAM bandwidth is the main bottleneck. But the price is ridiculous.
Reply on news.ycombinator.com