YuE2-3B (MLX, 6-bit, NAR 8-bit)
Derived from a copy of m-a-p/YuE2-3B, via ahmadw/YuE2-3B-MLX, by m-a-p. This is not an official release.
Changes
Quantised to 6 bit (AR blocks, LM head) and 8 bit (NAR blocks), group size 64. No retraining.
Licence
Creative Commons Attribution-NonCommercial 4.0, as the source — see LICENSE.
Non-commercial use only, with attribution, as the licence requires. The licence text in LICENSE includes the licensors' additional permission for individual creators.
All rights to the model remain with its authors.
SHA256SUMS, where present, lists the checksum of every file.
- Downloads last month
- -
Model size
4B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Audante/YuE2-3B-MLX-6bit-nar8
Base model
m-a-p/YuE2-3B