Update README.md
Browse files# Lens-Turbo-MLX-6bit
This repository contains the 6-bit quantized version of Microsoft's Lens-Turbo text-to-image model, optimized for Apple Silicon using MLX.
Lens-Turbo is a fast, lightweight 3.8B parameter text-to-image transformer. Quantized to 6-bit, the model size is reduced to approximately 3.3 GB, allowing it to run smoothly on Macs with 8GB or 16GB of unified memory without triggering Metal GPU watchdog timeouts.
## Model Details
- **Original Model:** [microsoft/Lens-Turbo](https://huggingface.co/microsoft/Lens-Turbo)
- **MindCraft Studio:** [MindCraft Studio Homepage](https://themindstudio.cc/mindcraft)
- **Quantization:** 6-bit weight-only quantization (quantize=6) via MLX.
- **Inference Steps:** Recommended 4 steps.
- **Guidance Scale:** 1.0 (CFG is disabled/forced to 1.0 for the Turbo architecture).
## How to Use in MindCraft Studio
1. Open MindCraft Studio.
2. Go to **Settings** -> **Model Library** -> **Import Local Model**.
3. Point to this directory.
4. The model will show up as **Lens-Turbo** and is ready for high-speed generation.
## Credits & References
- **Original Model:** [microsoft/Lens-Turbo](https://huggingface.co/microsoft/Lens-Turbo)
- **MindCraft Studio:** [themindstudio.cc/mindcraft](https://themindstudio.cc/mindcraft)
- **MLX Framework:** [Apple Machine Learning Research](https://github.com/ml-explore/mlx)