News for hackers. Stuff that matters.

A comment on Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac. Parent comment

Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by trollbridge on Wednesday July 29, 2026 @01:10PM (#49100215)
Please don’t use Ollama.

https://sleepingrobots.com/dreams/stop-using-ollama/

[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by reddguard on Wednesday July 29, 2026 @01:52PM (#49100743)
Doesn't Ollama use llama.cpp so their point stands even if they used it directly?
[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by cwillu on Wednesday July 29, 2026 @03:00PM (#49101569)
It wouldn't be the first time ollama's llama.cpp fork reintroduced bugs and was missing important optimizations.
[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by reddguard on Thursday July 30, 2026 @09:19AM (#49109593)
lol jealous hater
[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by cwillu on Thursday July 30, 2026 @11:29PM (#49118673)
Huh?
[ Parent | on HN ]
Re:Show HN: Open-source engine running Gemma 4 26B in 2 GB R... by trollbridge on Thursday July 30, 2026 @10:26AM (#49110495)
No, because Ollama is buggy. The first step to answering GPC’s question is to try using an up to date llama.cpp.
[ Parent | on HN ]