10-15-2026, 12:34 AM
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of PyTorch and M3 Max felt surprisingly usable once I tuned around KV cache pressure.
If someone wants the exact settings I can clean them up and post them.
This isn't revolutionary, but the combination of PyTorch and M3 Max felt surprisingly usable once I tuned around KV cache pressure.
If someone wants the exact settings I can clean them up and post them.
measure twice, benchmark three times