LocalLLaMA

2825 readers

22 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

founded 2 years ago

MODERATORS

[email protected]

Models not loading into RAM (lemmy.ml)

submitted 1 month ago by [email protected] to c/[email protected]

10 comments fedilink hide all child comments

I didn't expect a 8B-F16 model with 16GB on disk could be run in my laptop with only 16GB of RAM and integrated GPU, It was painfuly slow, like 0.3 t/s, but it ran. Then I learnt that you can effectively run a model from your storage without loading into memory and checked that it was exactly the case, the memory usage kept constant at around 20% with and without running the model. The problem is that gpt4all-chat is running all the models greater than 1.5B in this way, and the difference is huge as the 1.5b model runs at 20 t/s. Even a distilled 6.7B_Q8 model with roughly 7GB on disk that has plenty of room (12GB RAM free) didn't move the memory usage and it was also very slow (3 tokens/sec). I'm pretty new to this field so I'm probably missing something basic, but I just followed the instrucctions for downloading it and compile it.

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

[–] [email protected] 1 points 1 month ago (1 children)

Why don't you just use ollama?

[–] [email protected] 1 points 1 month ago

I don't like intermediaries ;) Fortunately I compiled llama.cpp with the Vulkan backend and everything went smooth and now I have the option to offload to the GPU. Now I will test performance CPU vs CPU+GPU. Downloaded deepseek 14b and is really good, the best I could run so far in my limited hardware.