AI Radar
Support
LiveUpdated 2026-09-21 19:14 UTC

BREAKING: The M5 Ultra is SLOWER than 2x DGX Sparks both on decode & prefill when…

BREAKING: The M5 Ultra is SLOWER than 2x DGX Sparks both on decode & prefill when testing on GLM 5.3 Flash. M5 Ultra:…

This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.

BREAKING: The M5 Ultra is SLOWER than 2x DGX Sparks both on decode & prefill when testing on GLM 5.3 Flash. M5 Ultra: Decode (unclear if prose or not) - 28 tok/s Prefill - 1016 tok/s 2x DGX Sparks: Decode on prose - 39 tok/s Prefill - 1700 tok/s The DGX Sparks numbers are from my own recipe. The sparks are 1.39x faster in decode and 1.67x faster in prefill! Doesn't mean things can't be improved on the Mac, but as it stands right now, 2x DGX Sparks beat it decisively. My GLM 5.3 Flash EXL3 recipe: https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Sparks Source: https://macstories.net

Posted by Mia (32.2k followers) 1 h ago · 191 likes · 9.4k views · view the original post on X. Kept by the AI Radar as AI infra & evals. Tools mentioned: glm-5.3-flash-exl3-2x-dgx-sparks.

More AI work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 39.8k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 19:14 UTC. Full method.