speakleash
/

Bielik-11B-v3.1-Instruct-MLX-4bit

4-bit precision

Model card Files Files and versions

Bielik-11B-v3.1-Instruct MLX-4bit

Quantized version of speakleash/Bielik-11B-v3.1-Instruct. Format: MLX 4-bit weights.

Downloads last month: 47

Safetensors

Model size

11B params

Tensor type

U32

·

BF16

·

MLX

Hardware compatibility

Log In to add your hardware

4-bit

Inference Providers NEW

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

Model tree for speakleash/Bielik-11B-v3.1-Instruct-MLX-4bit

Base model

speakleash/Bielik-11B-v3-Base-20250730

Finetuned

speakleash/Bielik-11B-v3.1-Instruct

Quantized

(7)

this model

Collection including speakleash/Bielik-11B-v3.1-Instruct-MLX-4bit

Bielik-11B-v3.1

A collection of models based on Bielik-11B-v3.1 - instruct and quantized versions. • 8 items • Updated 1 day ago • 6