AI

4142 readers

1 users here now

Artificial intelligence (AI) is intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals, which involves consciousness and emotionality. The distinction between the former and the latter categories is often revealed by the acronym chosen.

founded 3 years ago

LLM ASICs on USB sticks? (lemmy.ml)

submitted 5 months ago by [email protected] to c/[email protected]

13 comments fedilink hide all child comments

Source: nostr

https://snort.social/nevent1qqsg9c49el0uvn262eq8j3ukqx5jvxzrgcvajcxp23dgru3acfsjqdgzyprqcf0xst760qet2tglytfay2e3wmvh9asdehpjztkceyh0s5r9cqcyqqqqqqgt7uh3n

Paper: https://arxiv.org/abs/2406.02528

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 0 points 5 months ago (1 children)

That's weird, maybe I actually am doing something wrong. Is it because I'm using GGUF models maybe?

[–] [email protected] 0 points 5 months ago

llama2 gguf with 2bit quantisation only needs ~5gb vram. 8bits need >9gb. Anything inbetween is possible. There are even 1.5bit and even 1bit options (not gguf AFAIK). Generally fewer bits means worse results though.