---
language: en
library_name: mlx
pipeline_tag: image-text-to-text
tags:
- mlx
base_model:
- SulphurAI/Sulphur-2-base
base_model_relation: quantized
---

This model is an MLX conversion quantized to q4 for the prompt enhancer included with [Sulphur-2-base](https://huggingface.co/SulphurAI/Sulphur-2-base).  It's tested in LM Studio, and roughly 3x-4x the tokenization rate vs. running the original GGUF model on Apple M-series Macs.

To use, download the files and place them in your LM Studio models directory using the "owner/model" path structure other models use, or just use LM Studio to download directly.

Or use HF Hub and just symlink it

``` bash
hf download MLXBits/sulphur-prompt-enhancer-uncensored-mlx-q4
mkdir -p $HOME/.lmstudio/models/sulphur/prompt-enhancer-uncensored-mlx-q4
ln -s $HOME/.cache/huggingface/hub/models--MLXBits--sulphur-prompt-enhancer-uncensored-mlx-q4/snapshots/<snapshot hash> $HOME/.lmstudio/models/sulphur/prompt-enhancer-uncensored-mlx-q4
```