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

[reddguard]

Doesn't Ollama use llama.cpp so their point stands even if they used it directly?

[trollbridge → reddguard]

No, because Ollama is buggy. The first step to answering GPC’s question is to try using an up to date llama.cpp.

[cwillu → reddguard]

It wouldn't be the first time ollama's llama.cpp fork reintroduced bugs and was missing important optimizations.

[reddguard → cwillu]

lol jealous hater

[cwillu → reddguard]

Huh?