---
library_name: mlx
tags:
- mlx
- oq
- quantized
base_model:
- LiquidAI/d1-3B
---

# d1-3B-oQ4e-fp16

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.7.0) mixed-precision quantization.

## Quantization details

- **Model type**: lfm2_vl
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors