Y
Hacker News
new
|
ask
|
show
|
jobs
by
eurekin
912 days ago
I tried an hour ago and had a can't load model error. Everything up to date. Is there any special step?
2 comments
mmcclure
912 days ago
Tried `ollama pull mixtral` just now and it seems to be working, albeit pretty slowly.
link
Casteil
912 days ago
How much RAM do you have? Mixtral is a beast and the non quantized model wants 40GB+ of memory.
link
eurekin
912 days ago
Ah, that might be it! I have only 32
link
ukuina
911 days ago
The q2 should fit.
link