FlashLabs
/

Chroma-4B

feature-extraction

Speech-to-Speech

Model card Files Files and versions

Created ONNX version that seems to require a lot less VRAM

#17

by fwaris - opened Jun 28

Jun 28

https://github.com/fwaris/Chroma_ONNX

Was able to run it on a 3080 with 16GB of VRAM (+ 2GB shared memory).

Jun 30

BTW thanks for sharing. This is a great model / system!

fwaris changed discussion status to closed Jun 30

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