exolabs/nemotron-3-super-120b-a12b-mlx-q4-5-dequant-bf16

Public dequantized BF16 export for vLLM validation.

• Internal model id: nemotron-3-super-120b-a12b-mlx-q4-5
• MLX source: inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4.5
• Original HF comparison model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
• 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.