Comment

Comment on Elon Musk’s Grok Goes Haywire, Boasts About Billionaire’s Pee-Drinking Skills and ‘Blowjob Prowess’

Thanks a ton, saves me having to navigate the slopped up search results (‘AI’ as a search term is SEOd to death and back a few times)

I dunno what card you have now, but hybrid CPU+GPU inference is the trend days.

That system has the 3080 12GB and 64GB RAM but I have another 2 slots so I could go up to 128GB. I don’t doubt that there’s a GLM quant model that’ll work.

Is ollama for hosting the models and LM Studio for chatbot work still the way to go? Doesn’t seem like there’s much to improve in that area once there’s software that does the thing.

source

Sort:hotnew top

brucethemoose@lemmy.world ⁨3⁩ ⁨weeks⁩ ago
And IMO… your 3080 is good. It’s very well supported. It’s kinda hard to upgrade, in fact, as realistically you’re either looking at a 4090 or a used 3090.

source
brucethemoose@lemmy.world ⁨3⁩ ⁨weeks⁩ ago
Oh no, the software is everything, and ollama is awful. It’s enshittifying: don’t touch it with a 10 foot pole.

Speeds are basically limited by CPU RAM bandwidth. Hence you want to be careful doubling up RAM, and doubling it up can the max speed (and hence cut your inference speed).

Anyway, start with this. Pick your size, based on how much free CPU RAM you want to spare:

huggingface.co/ubergarm/GLM-4.5-Air-GGUF

The “dense” parts will live on your 3080 while the “sparse” parts will run on your CPU. The backend you want is this, specifically the built-in llama-server:

github.com/ikawrakow/ik_llama.cpp/

Regular llama.cpp is fine too, but it’s quants just aren’t quite as optimal or fast.

It has two really good built-in web UIs: the “new” llama.cpp chat UI, and mikupad, which is like a “raw” notebook mode more aimed at creative writing. But you can use LM Studio if you want, or anything else; there are like a bazillion fronted out there.

source