If these models reach quality of Opus 4.5, then DGX could be a good alternative for serious dev teams to run local models. It is not that expensive and has short time to make ROI
If these models reach quality of Opus 4.5, then DGX could be a good alternative for serious dev teams to run local models. It is not that expensive and has short time to make ROI
Memory bandwidth is the biggest L on the dgx spark, it’s half my MacBook from 2023 and that’s the biggest tok/sec bottleneck