Apple M6 has 80-100 TOPS.
Qualcomm Cloud AI 100 Ultra has 800 TOPS, almost 10 times more.
This could be very fast at running embedding models (if it supports the right modes)
Considering that memory bandwidth is the most important for inference for most neural networks, that matters more.
{"deleted":true,"id":50372347,"parent":50371651,"time":1793831105,"type":"comment"}