shanginn
/

Luminum-v0.1-123B-mlx-quantized-4bit

4-bit precision

Model card Files Files and versions

Quantized MLX model based on FluffyKaeloky/Luminum-v0.1-123B

Downloads last month: -

Safetensors

Model size

19B params

Tensor type

F16

·

U32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shanginn/Luminum-v0.1-123B-mlx-quantized-4bit

Base model

FluffyKaeloky/Luminum-v0.1-123B

Quantized

(5)

this model