Sorry for the off topic question, but does anyone know how to buy consumer hardware optimal for running emerging open source chat models with the largest parameter chat models possible?

Would it be more cost effective to try to buy an absurd amount of ram and run on the cpu?

Or buy an Nvidia card with the biggest capacity available?

Or maybe buy a Mac with the most memory you can get?

Install https://github.com/oobabooga/text-generation-webui, update pytorch and llamacpp-python, and you should be able to run pretty much all models out there, in all formats, both on GPU and CPU. CPU on a MAC gives you the fastest speed, but you should pass the correct --threads argument (investigate how many performance cores you've got). GPU is slower, but more energy efficient. https://github.com/mlc-ai/mlc-llm gives me way better GPU performance compared to oobabooga, but they only support a couple of models right now, - it's worth following their progress though.

If you're after the raw performance, I suggest using GGML models (meant for llama.cpp, but it's bundled in textgen, so you can use it there with the convenience of a web ui). q4_0 is the fastest quantization, while the q5_1 is the best quality right now.

If the GGML is not available, you can generate it quite easily from the safetensors yourself (not the you need enough RAM to load the model in pytorch though).

With 16GB RAM you can run any 13G model, as long as it's quantized to 4/5 bits. 32GB RAM allows you running 30/33G models and 64GB RAM - 65G models. 30G and 60G models are way more useful for real world tasks, but they are more expensive to train, so there aren't as many to choose from compared to 7/13. 7B and anything less is a toy in my opinion while 13B is good enough for experimentation and prototyping.