The short version
An open-source Mac engine that streams Gemma 4 experts from storage to minimize RAM use.
From the HackerLinks archive
An open-source Mac engine that streams Gemma 4 experts from storage to minimize RAM use.
The short version
An open-source Mac engine that streams Gemma 4 experts from storage to minimize RAM use.
Why it caught our attention
A firsthand benchmark reported fast, graceful performance under memory pressure on an M4 Max.
Where it surfaced on Hacker News
“Ran this on a 64 GB M4 Max MacBook.”
pwython · recommendation · first hand use
Direct HN comment
Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac