10-04-2026, 12:18 AM
I don't think that's the whole story. I get why that seems right, but on dual 3090 the bottleneck felt elsewhere.
M3 Max • MLX • local-first
|
prefill bottlenecks on longer prompts on A6000
|
|
« Next Oldest | Next Newest »
|
Users browsing this thread: 1 Guest(s)