What is better: higher quantiation or higher parameter count?
What is better: higher quantiation or higher parameter count?
For example, does a 13B parameter model at 2_K quantiation perform worse than a 7B parameter model at 8bit or 16bit?
https://github.com/ggerganov/llama.cpp#quantization
https://github.com/ggerganov/llama.cpp/pull/1684
Regarding your question: 13B 2_K seems to be on par with 7B 16bit and 8bit. Not much of a difference between all those. (Look at the perplexity values. Lower is better.) The second link has a nice graph.
Most people don't go as low as 2bit though. Look at the graph, below 4bit things start to deteriorate.
That graph is great. Very easy to understand. Thank you!
These are good sources, to add one more, the GPTQ paper talks a lot about perplexity at several quantization and model sizes: