the size of llama weight

[Gelercatty]

hi there！im trying to develop based on your fancy project,but i faced some questions
i wannder to figure out the GPU requirements to run your model, i think the raw llama13b is too heavy to combine this project with other applications,
Whether to provide quantized model operations to reduce the GPU burden?
thanks a lot in advance QAQ!

[Gelercatty]

Does it support the quantized llama model to run? i would appreciate it for your reply