Tagged with apple-silicon

• Running a 744B Model on a Laptop, Then Telling the Author Not to Fix That Bug

  colibri claims you can run GLM-5.2, all 744 billion parameters, on about 25GB of RAM. I actually ran it on an M1 Max. Seven seconds per token. Three counterintuitive findings came out of it, and one of them turned my upstream report from "please fix this bug" into "please don't".

  Jul 30, 2026moeapple-siliconbenchmarklocal-llm

• The Paper Says ARM Support. I Might Be the First to Actually Compile It

  Microsoft released VibeVoice-ASR-BitNet, a speech recognition model that claims real-time transcription on CPUs, "targeting both ARM and x86". I put that to the test on an M1 Max, and debugged my way from a compile error to a beautiful NaN fingerprint, finding three upstream bugs along the way. A story about how to read model cards.

  Jul 27, 2026asrbitnetdebuggingapple-silicon