lightsofapollo
/

omnivoice-mlx-q8-g64

8-bit precision

Model card Files Files and versions

omnivoice-mlx-q8-g64 / tokenizer.json

Commit History

OmniVoice MLX q8-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16

b50cab9
verified

lightsofapollo commited on 3 days ago