metadata
library_name: mlx
license: apache-2.0
base_model: lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
base_model_relation: quantized
tags:
- mlx
- oQe
- enhanced
- mixed-precision
- reasoning
- distilled
- moe
track_downloads: true
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8e-fp16
This model was quantized using oQ (oMLX v0.3.8) mixed-precision quantization.
Quantization details
- Model type: qwen3_5_moe
- Bits: 8
- Group size: 64
- Format: MLX safetensors