Is it possible to run NF4 checkpoints with LoRA on 12gb VRAM?

OS: W10 LTSC
RAM: 16gb
GPU: Nvidia 3060 12gb VRAM

I keep running into OOM errors when i try to use a single LoRA:


Is there any setting i am applying wrongly? I have seen people run NF4 checkpoints on 6-8gb VRAM so i find weird a single LoRA would take 4-6gb VRAM to run.

I would post a log but i cannot find the log file.

No source file, test, or log path is identified; begin by reproducing the OOM with the reported Windows 10 LTSC, 16 GB RAM, Nvidia 3060 12 GB VRAM setup, an NF4 checkpoint, and one LoRA. Collect the application's log and configuration details, then determine whether the reported settings or workload explain the memory use; done means a confirmed cause or a clear supported configuration.

Written by the indexing model from the issue text.