anquachdev
/

hibiki-1b-mlx-q4

speech-to-speech

Model card Files Files and versions

Hibiki 1B MLX Q4

Weight-only quantization of the language model from the artifact revision unknown.

Quantization: Q4, group size 32
Quantized modules: compatible MLX Linear layers only
Unchanged: Mimi codec, embeddings, normalisation layers, tokenizer

Downloads last month: 22

MLX

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 anquachdev/hibiki-1b-mlx-q4

Base model

kyutai/hibiki-1b-mlx-bf16

Quantized

(2)

this model