Comment by willXare 2 days ago At 128 tokens, you’re benchmarking the overture, not the opera. 1 comment willXare Reply lloyd-christmas 2 days ago I thought the same thing when I started using locals, but the reality is that - for a given context depth - the token generation speed doesn't change whether it's 128 or 8000, it just lengthens the benchmark run time.
lloyd-christmas 2 days ago I thought the same thing when I started using locals, but the reality is that - for a given context depth - the token generation speed doesn't change whether it's 128 or 8000, it just lengthens the benchmark run time.
I thought the same thing when I started using locals, but the reality is that - for a given context depth - the token generation speed doesn't change whether it's 128 or 8000, it just lengthens the benchmark run time.