lightsofapollo
/

omnivoice-mlx-q8-g64

8-bit precision

Model card Files Files and versions

omnivoice-mlx-q8-g64 / audio_tokenizer

403 MB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

lightsofapollo's picture

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

b50cab9 verified 4 days ago

config.json

2.53 kB
OmniVoice MLX q8-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16 4 days ago
model.safetensors

403 MB
xet

OmniVoice MLX q8-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16 4 days ago
preprocessor_config.json

206 Bytes
OmniVoice MLX q8-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16 4 days ago