---
license: other
private: true
---

# exolabs/gemma-4-e2b-it-8bit-text-dequant-bf16

Private dequantized BF16 export for vLLM validation.

- Internal model id: `gemma-4-e2b-it-8bit`
- MLX source: `mlx-community/gemma-4-e2b-it-8bit`
- Original HF comparison model: `google/gemma-4-E2B-it`
- Export dtype: `bfloat16`
- Text-only export: `True`

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