It's GPU performance.
Spin up ollama and run some inference on your 5-year-old intel macbook. You won't see 4000x performance improvement (because performance is bottlenecked outside of the GPU), but you might be in the right order of magnitude.
Spin up ollama and run some inference on your 5-year-old intel macbook. You won't see 4000x performance improvement (because performance is bottlenecked outside of the GPU), but you might be in the right order of magnitude.
[1] The memory bandwidth is fine for CPU workloads, but not for GPU / NN workloads.
"Look how many times faster our car is![1]"
[1] Compared to a paraplegic octogenarian in a broken wheelchair!"