Hacker News new | ask | show | jobs
by sebastiennight 228 days ago
Could you share which Macbook model? And what context size you're getting.
1 comments
onion2k 228 days ago
I just checked gpt-oss:20b on my M4 Pro 24GB, and got 400.67 tokens/s on input and 46.53 tokens/s on output. That's for a tiny context of 72 tokens.
link
sebastiennight 226 days ago
This message was amazing and I want about to hit [New Tab] and purchase one myself until the penultimate word.
link