LocalLLaMA
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.
Rules:
Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.
Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.
Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.
Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.
view the rest of the comments
Possibly. Vulkan would be compatible with the system and would be able to take advantage of iGPUs. You'd definintely want to look into whether or not you have any dedicated vRAM thats DDR5 and just use that if possible.
Explanation: LLMs are extremely bound by memory bandwidth. They are essentially giant gigabyte-sized stores of numbers which have to be read from memory and multiplied by a numeric representations of your prompts...for every new word you type in and every word you generate. To do this, these models constantly pull data in and out of [v]RAM. So, while you may have plenty of RAM, and decent amounts of computing power, your 780m probably won't ever be great for LLMs, even with Vulkan, because you don't have the memory bandwidth to keep it busy.
roughly, for a small model
Thanks for the write-up! Specifically I'm running a framework 13 7840U, so it's ddr5, and that iGPU has no dedicated vram, it shares the main system ram.
I'm not looking for ridiculous performance, right now for small models I'm seeing probably 3 ish words per second. But when I put bigger models in, it starts to get ridiculously slow. I'm fine waiting around, really I'm just playing with it because I can. But that's entering no fun territory haha