Simon Willison's blog post has a screenshot. It's worth a read. https://simonwillison.net/2023/Nov/29/llamafile/

Thank you, is there a way to select a different model? How does the model perform? Just general question if anyone else knows the answers while I try and clear space on my laptop ( why these things fill up so fast!)

Token/second performance has been excellent for me.

You can use this to run any if the thousands of of GGUF models on Hugging Face, see note here: https://simonwillison.net/2023/Nov/29/llamafile/#llamafile-t...