alt Hacker NewsCerebras already runs large models like Kimi 2.6 or GLM at like 30x speed. 100 times is next year, not six years.
You can actually test it out on their website, just imagine 3 x faster and maybe 15% smarter.
Replies
keepupnow • today at 1:42 AM
This.
Cerebras is literally the entire wafer, so it can't get bigger. So where is the jump from 30x to 100x coming from? Node improvements only yield like 10-20% gains these days...