lightsofapollo
/

omnivoice-mlx-q4-g64

4-bit precision

Model card Files Files and versions

omnivoice-mlx-q4-g64

Commit History

OmniVoice MLX q4-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16

c2c7cf4
verified

lightsofapollo commited on 5 days ago

initial commit

6ce2d46
verified

lightsofapollo commited on 5 days ago