LLM Benchmarks on my Hardware

LLM Performance on my Hardware (llama.cpp) #

TODO

Test on CPU:

different nodes
cpu types (kvm, qemu, and host)
number of cpu cores

GPU:

Intel i5-1240p iGPU (1.3 GHz, 80 exec units), 3200 MHz shared RAM
Intel i5-12450h iGPU (1.2 GHz, 48 exec units), 3200 MHz shared RAM