Translation
Transformers
Safetensors
hy_v3
text-generation

Request: oQ4 (MLX) quantization for Apple Silicon?

#1
by 0xtimi2233 - opened

Hi,

Great model! Is anyone planning to convert this model to the oQ4 (MLX) format using omlx?
(Ref: https://github.com/jundot/omlx/blob/main/docs/oQ_Quantization.md)

This format would be perfect for running it locally on Mac.

Thanks!

Hi @bearzi , could you help create a standard oQ4 (and maybe oQ6) quant for this new Hy-MT2-30B model? I really want to run it locally on Mac, but my own hardware just can't handle a 30B calibration.

You've done amazing work with oMLX quants for the community, so it would be awesome if you could look into this one when you have some time. Thanks a lot!

0xtimi2233 changed discussion status to closed

Sign up or log in to comment