[!IMPORTANT] This quantization was uploaded on 2026-05-06 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.5-4B-oQ2-fp16

Quantization details

• Model type: qwen3_5
• Bits: 2
• Group size: 64
• Format: MLX safetensors