[!IMPORTANT] This quantization was uploaded on 2026 05 13 and replaces a previous version. If you downloaded this model before this date, please re download for the updated weights. Qwen3.6 27B oQ8 mtp This model was quantized using oQ (oMLX v0.3.9.dev2) mixed precision quantization. Quantization details Model type : qwen3 5 Bits : 8 Group size : 64 Format : MLX safetensors
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy