Hacker News new | ask | show | jobs
by october8140 497 days ago
You can get 1t/s on a raspberry pi.

https://youtu.be/o1sN1lB76EA?si=i8ecEBjLdV0zewFQ

1 comments

this has nothing to do with the full 671B and the ollama models are distilled qwen2.5
I appreciate both of these comments, thank you both.