this post was submitted on 09 Oct 2023
34 points (100.0% liked)

Futurology

0 readers
1 users here now

founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] Speculater@lemmy.world 0 points 1 year ago (4 children)

The problem is most of these models need like a terabyte of VRAM... And consumers have about 8-24GB.

[–] sudo22@lemmy.world 2 points 1 year ago (3 children)
[–] Speculater@lemmy.world 4 points 1 year ago (2 children)

This specific one says it'll run on 24GB actually. But some are just crazy big.

[–] Lugh@futurology.today 2 points 1 year ago* (last edited 1 year ago) (1 children)

There are smaller models that can run on most laptops.

https://www.maginative.com/article/stability-ai-releases-stable-lm-3b-a-small-high-performance-language-model-for-smart-devices/

In benchmarks this looks like it is not far off Chat-GPT 3.5.

[–] BetaDoggo_@lemmy.world 1 points 1 year ago

It's not even close, less than half of 3.5's 85.5% in ARC. Some larger Open models are competitive in Hellaswag, TruthfulQA and MMLU but ARC is still a major struggle for small models.

3Bs are kind of pointless right now because the machines with processors capable of running them at a usable speed probably have enough memory to run a 7B anyway.