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.
Did you try your CPU?
Also try Deepseek 14b. It will be much faster.
Yes, gpt4all runs it in cpu mode, the gpu option does not appear in the drop-down menu, which means the gpu it’s not supported or there is an error. I’m trying to run the models with the SyCL backend implemented in llama.cpp that performs specific optimizations for cpu+gpu with the Intel DPC++/C++ Compiler and the OneAPI Toolkit.
ok, I’ll test it out.
Why don’t you just use ollama?
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.