Lowkey-Loki
/

reka-flash-3-mlx-3bit

Model card Files Files and versions

Quantized 3bit MLX version of https://huggingface.co/RekaAI/reka-flash-3

Downloads last month: 15

Safetensors

Model size

21B params

Tensor type

U32

·

F16

·

MLX

Hardware compatibility

Log In to add your hardware

3-bit

Inference Providers NEW

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

Model tree for Lowkey-Loki/reka-flash-3-mlx-3bit

Base model

RekaAI/reka-flash-3

Quantized

(29)

this model