13 points | by jacquesm 2 hours ago
5 comments
> RTX Pro 6000 Blackwell has 96GB of GDDR7 VRAM
https://www.apple.com/shop/buy-mac/mac-studio/m3-ultra-chip-...
LLMs can re-write and cross-translate software really well. Why does CUDA still have a $11k price premium?
It depends how you price the ability to run a particular model at all, vs run the model quickly and serve several parallel streams.
They're both good value (or crazy expensive) depending on how you look at it.
You can get 5-10x the perf out of the blackwell under the right workloads.
The Blackwell is going to be a lot faster for the same memory capacity than a Mac Studio, surely?
Because a lot of people are buying them at that price.
Just when Cyberpunk gets almost bug-free, the price for a decent Gpu to run it smoothly is skyrocketing. #doooh
https://www.apple.com/shop/buy-mac/mac-studio/m3-ultra-chip-...
LLMs can re-write and cross-translate software really well. Why does CUDA still have a $11k price premium?
It depends how you price the ability to run a particular model at all, vs run the model quickly and serve several parallel streams.
They're both good value (or crazy expensive) depending on how you look at it.
You can get 5-10x the perf out of the blackwell under the right workloads.
The Blackwell is going to be a lot faster for the same memory capacity than a Mac Studio, surely?
Because a lot of people are buying them at that price.
Just when Cyberpunk gets almost bug-free, the price for a decent Gpu to run it smoothly is skyrocketing. #doooh