---
library_name: mlx
tags:
- mlx
- oq
- quantized
---

# GLM-5.3-Flash-UNCENSORED-oQ4e-mtp

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.7.0.dev2) mixed-precision quantization.

## Quantization details

- **Model type**: glm5_next
- **Bits**: 4
- **Group size**: 64
- **Format**: MLX safetensors