---
library_name: mlx
tags:
- mlx
- oq
- quantized
- omlx
- oQ4e
base_model:
- poolside/Laguna-XS-2.1
---

> [!IMPORTANT]
> This quantization was uploaded on **2026-08-01** and replaces a previous version.
> If you downloaded this model before this date, please re-download for the updated weights.

# Laguna-XS-2.1-oQ4e

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.5.4rc2) mixed-precision quantization.

## Quantization details

- **Model type**: laguna
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors

## Quantization methods...

I quantized via oMLX on my macbook pro M3 Max 48 GB machine from the base Laguna-XS-2.1 data and it worked somehow ...