Hacker News new | ask | show | jobs
by halflings 807 days ago
The # of chips is not the most important metric.

Most important, even ignoring latency, is throughput (tokens) per $$$. And according to their own benchmark [1] (famous last words :)), they're quite cost efficient.

[1] https://www.semianalysis.com/p/groq-inference-tokenomics-spe...