mlx-MOSS-Transcribe-Diarize 8bit

8bit MLX weight-only quantized variant of vanch007/mlx-MOSS-Transcribe-Diarize.

Quantization uses MLX affine quantization with bits=8 and group_size=64 on the text backbone, excluding the Whisper audio encoder and VQ adaptor.

python -m moss_transcribe_diarize.mlx.cli /path/to/input.wav \
  --model plaincompute/mlx-MOSS-Transcribe-Diarize-8bit \
  --out-dir runs/mlx_8bit_example

Downloads last month: 16

Safetensors

Model size

0.9B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized

Model tree for plaincompute/mlx-MOSS-Transcribe-Diarize-8bit

Base model

OpenMOSS-Team/MOSS-Transcribe-Diarize

Finetuned

vanch007/mlx-MOSS-Transcribe-Diarize

Finetuned

(3)

this model