[alfonsodev]

good to hear! Do you mind sharing your setup and tokens / seconds performance ?

[lreeves]

I'm running the unquantized base model on 2xA6000s (Ampere gen, 48GB each). Runs at about 25 tokens/second.

[NitpickLawyer]

FYI they also released FP8 quants, and those should be faster on your setup (we have the same). As long as you keep kv at 16bit, FP8 should be close-to-lossless compared to 16bit, but with more context available and faster inference speed.