exolabs/deepseek-v4-flash-2bit-dq-dequant-bf16

Public dequantized BF16 export for vLLM validation.

  • Internal model id: deepseek-v4-flash-2bit-dq
  • MLX source: unknown
  • Original HF comparison model: unknown
  • Export dtype: unknown
  • Text-only export: False

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

Downloads last month
-
Safetensors
Model size
284B params
Tensor type
I64
·
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support