top | item 45592183

(no title)

nik736 | 4 months ago

If you have enough memory to load a model, but not enough bandwidth to handle it, you will get a very low token/s output.

discuss

order

Rohansi|4 months ago

You can also have enough bandwidth but be compute limited and get lower performance than expected. This is more likely to be the case for Apple Silicon vs. high power GPUs.