This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.
Quantization details
Model type: qwen3_5_moe
Bits: 4
Group size: 64
Format: MLX safetensors
Overview
This is a hybrid mixed-precision oQ4 quantization of the agentic coding model Ornith-1.0-35B, grafted with the high-efficiency Multi-Token Prediction (MTP) lookahead blocks from Qwen3.6-35B-A3B.
