[!IMPORTANT] This quantization was uploaded on 2026-05-20 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.6-35B-A3B-oQ8-fp16-mtp

Quantization details

• Model type: qwen3_5_moe
• Bits: 8
• Group size: 64
• Format: MLX safetensors