09-26-2026, 06:13 PM
Appreciate the detail. That matches what I saw on 5090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
measure twice, benchmark three times
|
eval setup for local models on M3 Max
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
eval setup for local models on M3 Max - by griffinloom66 - 09-24-2026, 05:37 PM
Re: eval setup for local models on M3 Max - by cacheline - 09-26-2026, 06:13 PM
|
Users browsing this thread: 1 Guest(s)