@eyecreate looks to have slipped off the pin on right. Does it not push up back over it?
falken
joined 1 year ago
@FireTower "note taking in class" isn't going to tax even the entry level machine. Goes double of you use #linux. You can always upgrade later if needs change.
@[email protected] @[email protected] local LLM execution times can be very fast on recent consumer hardware. No need to send anywhere, just like their translation - do it all on-device.
As an example, with no optimization or GPU support, my @[email protected] (AMD) generates around 5 characters/sec from a 4 gigabyte pre-quantized model.
view more: next ›
@eyecreate hmm. Asked official Framework forum?