News for hackers. Stuff that matters.

A comment on Why your local LLM feels dumber than it is. Parent comment

Re:Why your local LLM feels dumber than it is by MrScruff on Saturday August 22, 2026 @05:46PM (#49404188)
I get around 20 tok/s, 4 bit quant, MTP, 4 bit KV cache quantisation. On an M4 Pro 48Gb.
[ Parent | on HN ]

There are no comments on this comment yet.