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, high-quality 3.8B parameter text-to-image model.
Model Details
- Original Model: microsoft/Lens-Turbo
- MindCraft Studio: MindCraft Studio Homepage
- 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 distilled Turbo architecture).
How to Use in MindCraft Studio
- Open MindCraft Studio.
- Go to Settings -> Model Library -> Import Remote Model.
- Point to this directory.
- The model will show up as
Lens (Turbo) and is ready for high-speed generation.
Credits & References
