[!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 (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 ...