WingNews logo WingNews
top | item 42883746

(no title)

mike31fr | 1 year ago

Running it on a MacBook with M1 Pro chip and 32 GB of RAM is quite slow. I expected to be as fast as phi4 but it's much slower.

discuss

order

mike31fr|1 year ago

With eval rate numbers:

- phi4: 12 tokens/s

- mistral-small: 9 tokens/s

On Nvidia RTX 4090 laptop:

- phi4: 36 tokens/s

- mistral-small: 16 tokens/s