Comment by sebastiennight 3 months ago Could you share which Macbook model? And what context size you're getting. 2 comments sebastiennight Reply onion2k 3 months 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. sebastiennight 3 months ago This message was amazing and I want about to hit [New Tab] and purchase one myself until the penultimate word.
onion2k 3 months 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. sebastiennight 3 months ago This message was amazing and I want about to hit [New Tab] and purchase one myself until the penultimate word.
sebastiennight 3 months ago This message was amazing and I want about to hit [New Tab] and purchase one myself until the penultimate word.
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.
This message was amazing and I want about to hit [New Tab] and purchase one myself until the penultimate word.