limegreenpeper1
/

Qwen3-4B-Novel-JP-MLX-8bit

Text Generation

8-bit precision

Model card Files Files and versions

original: https://note.com/holy_fox/n/n8d309d359f39

Downloads last month: 140

Safetensors

Model size

1B params

Tensor type

BF16

·

U32

·

MLX

Hardware compatibility

Log In to add your hardware

8-bit