09-21-2026, 07:12 PM
Quote:My first guess would be this: Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there. Once you know the plain pa
Interesting, I hadn't tried that. That matches what I saw on 4090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
still benchmarking everything
