Hans C Nelson 🗽(@HansCNelson):I do not understand this nonsense! Assuming that you need the privacy of running on your own hardware, why not just rent GPUs in the cloud on demand? Unless you're running the model flat out 24/7 for a very long time, it would be pretty hard to spend more than $71k on hardware rental. And REALLY hard if you just buy the tokens instead of renting the hardware.

2026.08.26 18:36

I do not understand this nonsense! Assuming that you need the privacy of running on your own hardware, why not just rent GPUs in the cloud on demand? Unless you're running the model flat out 24/7 for a very long time, it would be pretty hard to spend more than $71k on hardware rental. And REALLY hard if you just buy the tokens instead of renting the hardware.

Bleys Goodson@bleysg

2026.08.26 02:04

M5 Ultra just boxed in my projection of "When do we get frontier models at home?" Why? Because they're copying the DGX Spark model: Dare you to have just one. 512GB M5 Ultra is $17.7k in Oct. It will take 4x to run Kimi K3. Apple is supporting this arrangement. This will be the most economical way to run Kimi K3 "at home" ... $71K. That's not really an "at home" price for most of us, but before that the most economical option was looking like it would be 8x B300 in a DGX B300 for around $550k. That's a rack-mount beast needing power and cooling consideration, not a cool and quiet desktop box that can plug into any average circuit. The costs and practicalities made it a real consideration only for SMBs with serious on-prem requirements. A 4x M5 Ultra cluster can sit anywhere and give practically fast frontier level model performance, before the end of this year!