Comment Comment by halflings The # of chips is not the most important metric.Most important, even ignoring latency, is throughput (tokens) per $$$. And according to their own benchmark [1] (famous last words :)), they're quite cost efficient.[1] https://www.semianalysis.com/p/groq-inference-tokenomics-spe... parent halflings 2 years ago
Most important, even ignoring latency, is throughput (tokens) per $$$. 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...