2026-10-12 13:38 UTC
Replies (2)
-
@Skullgrid@lemmy.world 2026-10-13 01:52
I’m also impressed with GLM-5.3-Flash. This is similar to Claude Opus 4.8. It’s much smaller and cheaper than GLM-5.3, and still incredibly capable. It’s also actually feasible for an individual person to get hardware to run it, like if you can one day get your hands on a Mac Studio with 512GB of RAM. 512 GB of RAM?! My brother in christ I don’t even have 12 GB of ram! I don’t even have 512GB of SSD storage!
-
@DupaCycki@lemmy.world 2026-10-13 09:52
It’s also actually feasible for an individual person to get hardware to run it, like if you can one day get your hands on a Mac Studio with 512GB of RAM. From the article. Apple announced the M5 Ultra Mac Studio on August 26, 2026, with pre-orders open today and shipping on September 22. The headline number for local AI is 512GB of unified memory at 1.2 TB/s of memory bandwidth, starting at $5,499. modelfit.io/…/mac-studio-m5-ultra-512gb-local-llm… Can’t find any for sale, because it seems completely unavailable at the moment. That aside, I wouldn’t call a price point of $5500 USD ‘feasible’.