ghost

joined 1 month ago
[–] ghost@feddit.org 3 points 3 days ago

As others have already mentioned, try qwen2.5-cider. With 16 GB, you should be able to confortably fit a quantised version of the 14b variant into VRAM. You can also try the 32b variant, but it will be much slower because not all layers can be off-loaded to the GPU.

[–] ghost@feddit.org 22 points 1 week ago

Jellyfin is just so much better, imo. Much cleaner, less stuff that I don’t actually need.

I'm a plex pass lifetime owner, but I don’t regret switching to Jellyfin one bit.