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

# ToriiGate-0.5-oQ8

// this model might have the best VLM i've seen, especially for recognizing whatever is going on in artwork.

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.3.6) mixed-precision quantization.

## Quantization details

- **Model type**: qwen3_5
- **Bits**: 8
- **Group size**: 64
- **Format**: MLX safetensors