Modelpublic

swdjojo/LRM-3.2-MLX-oQ6e

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes16downloads

Model Card

[!IMPORTANT] This quantization was uploaded on 2026-08-14 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

LRM-3.2-MLX-oQ6e

This model was quantized using oQ (oMLX v0.6.0.dev1) mixed-precision quantization.

Quantization details

—Model type: qwen3_5
—Bits: 6
—Group size: 64
—Format: MLX safetensors