On: Run the strongest open-source LLM model: Llama3 70...

[p1esk]

I didn’t check, but iirc it was an fp16 model checkpoint which we converted to int8 for inference, so I assume 140GB?

[logicallee → p1esk]

Thanks, I finished downloading it (which took many hours) onto an external hard drive (by adding a HF_HOME environmental variable for where to store that cache). Its size was 262 GB.