[!IMPORTANT] This quantization was uploaded on 2026-10-13 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

NuExtract3-oQ8e-mtp

This model was quantized using oQ (oMLX v0.7.1.dev1) mixed-precision quantization.

Quantization details

• Model type: qwen3_5
• Bits: 8
• Group size: 64
• Format: MLX safetensors