News for hackers. Stuff that matters.

paprots

paprots on Hacker News

Re:Gemma 3 QAT Models: Bringing AI to Consumer GPUs on Sunday April 20, 2025 @03:00PM (#43745751)
The original gemma3:27b also took only 22GB using Ollama on my 64GB MacBook. I'm quite confused that the QAT took the same. Do you know why? Which model is better? `gemma3:27b`, or `gemma3:27b-qat`?