CoolFace
Modelpublic

exolabs/qwen3-5-9b-mlx-4bit-text-dequant-bf16

sourceHugging Faceotherupdated 3mo agoView on Hugging Face
0likes17downloads
Model Card

exolabs/qwen3-5-9b-mlx-4bit-text-dequant-bf16

Public dequantized BF16 export for vLLM validation.

  • —Internal model id: qwen3-5-9b-mlx-4bit
  • —MLX source: mlx-community/Qwen3.5-9B-MLX-4bit
  • —Original HF comparison model: Qwen/Qwen3.5-9B
  • —Export dtype: bfloat16
  • —Text-only export: False

This checkpoint is the result of dequantizing the quantized MLX checkpoint. It is not the original upstream BF16 checkpoint.