this post was submitted on 29 Nov 2025
6 points (100.0% liked)

Ollama - Local LLMs for everyone!

311 readers
2 users here now

A place to discuss Ollama, from basic use, extensions and addons, integrations, and using it in custom code to create agents.

founded 9 months ago
MODERATORS
 

tl;dr - Mac is 2x faster on a 1b model. Goes down in flames and is 1/2 as fast at 2b models.

I started running models of 1b, 2b, and 20b on an AMD, no GPU, 32gb ram. The Mac M2 only has 8gb ram. The Mac was using 4 cores and GPU heavily.

I tried Debian minimal and PopOS standard and saw no significant difference.

These tests have very little worth. It's the holiday. I'm tinkering with what's around the house.

no comments (yet)
sorted by: hot top controversial new old
there doesn't seem to be anything here