Replies: 1 comment
-
|
Well, using the Q3_K_S variant of LTX2.3 22b along with Gemma3 12b Q3_K_S makes it fit into the 32GB my laptop has. Q4_K_S results in an OOM kill. It's been running for several hours now and didn't finish the 1s of video yet. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Has anyone tried ltx2.3 inference on CPU? If yes, what was the peak memory usage [only CPU, no GPU] and how much time did it take? Also, what CPU and what mode did you use- t2v, i2v or flf2v?
Beta Was this translation helpful? Give feedback.
All reactions