“the bus width of data bits going in? It's really the model…” — Practical AI at 24:54
“the bus width of data bits going in? It's really the model on fitting into the GPU memory and not exceeding it. So unless you want to quantize your model, which we had a whole episode with Neural Magic, so I'd recommend people listen to that. That was really cool. But unless you're very careful, so quantization means…”
0:00
42:11