Sure, but I’m just playing around with small quantized models on my laptop with integrated graphics and the RAM was insanely cheap. It just interests me what LLMs are capable of that can be run on such hardware. For example, llama 3.2 3B only needs about 3.5 GB of RAM, runs at about 10 tokens per second and while it’s in no way comparable to the LLMs that I use for my day to day tasks, it doesn’t seem to be that bad. Llama 3.1 8B runs at about half that speed, which is a bit slow, but still bearable. Anything bigger than that is too slow to be useful, but still interesting to try for comparison.
I’ve got an old desktop with a pretty decent GPU in it with 24 GB of VRAM, but it’s collecting dust. It’s noisy and power hungry (older generation dual socket Intel Xeon) and still incapable of running large LLMs without additional GPUs. Even if it were capable, I wouldn’t want it to be turned on all the time due to the noise and heat in my home office, so I’ve not even tried running anything on it yet.
But 2K and 4K do refer to the horizontal resolution. There’s more than one resolution that’s referred to as 2K, for example 2048 x 1080 DCI 2K, but also 1920 x 1080 full HD, since it’s also almost 2000 pixels wide. The total number of pixels is in the millions, not thousands.
For 4K some common resolutions are 4096 x 2160 DCI 4K and 3840 x 2160 UHD, which both have a horizontal resolution of about 4000 pixels.