News for hackers. Stuff that matters.
Re:A 10 year old Xeon is all you need (for 26B-A4B MTP Draft... by anon-3988 on Monday June 01, 2026 @05:17AM (#48354425)
I am pretty sure llamacpp have their own benchmarking binary that you can use.
Re:A 10 year old Xeon is all you need (for 26B-A4B MTP Draft... by mft_ on Monday June 01, 2026 @06:46AM (#48355070)
llama-bench is part of the llama-cpp package, but from recent experimentation, the settings it is able to (or is documented to?) accept lag behind somewhat. Not sure whether it would accept all of the esoteric settings in the article?