Hacker News Reader

Comment by Exoristos | Hacker News Reader

"Muse Spark Open was optimized to run on Mac Studio with M5 Ultra, and together they’re the best way to run a powerful model on your own desktop."

View on HN

”Serve the model on either two Mac Studios, with M5 Ultra and 512GB of unified memory; or four Mac Studios with 256GB of unified memory, for a total of 1TB of unified memory, enough to hold a NVFP4 quantized version of Muse Spark Open”

Can not find any info on inference speed.

its around 20tps

Read it again. Two M5s.

Wait read that again. Two 512GB, unreleased model M5s.

This is gonna cost like 50k to run at home.

Why would anyone want to run an LLM on Apple's hardware? Why not buy an NVIDIA GPU?

Try to find a NVIDIA GPU with 256/512 GB of RAM.

Closer to ~$30K if I had to guess. A 256 version is $11,299.00 (2TB SSD, 256GB RAM, 36-core CPU, 80‑core GPU), so yeah, 4 of those would be close to $50K but the 96->256 RAM upgrade is $4K, if we assume 512 will be double that it's ~$15K/ea.

But yes, still a massive amount of money and that's before we know the TPS or any other stats.

The closest equivalent to something like that is a GB300 based workstation, those go from 90K and up.

How much does the engineers at Meta make? Spend enough time together with others making $250k+ and eventually you start suggesting that two 512 GB M5s is something you can put on your desktop. I mean, it's one banana, Michael. What could it cost? 10 dollars?

okay that's gonna be interesting to try

Reply on news.ycombinator.com