dit GGUF Q4 weight precision is U8?

by Marvin-0042 - opened 8 days ago

8 days ago

Thank you so much for making Mochi working in consumer GPU!!!

mochi_preview_dit_GGUF_Q4_0_v1.safetensors, i saw the breakdown weight precision are U8, not U4. Why is it?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment