| license: apache-2.0 | |
| base_model: Qwen/Qwen-Image | |
| pipeline_tag: text-to-image | |
| tags: [text-to-image, mflux, qwen, qwen-image, quantized, osaurus] | |
|  | |
| # Qwen-Image · mflux · 4-bit | |
| Official **OsaurusAI** 4-bit [mflux](https://github.com/filipstrand/mflux) build of [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) (Qwen, Apache-2.0), quantized by Osaurus with mflux 0.18. High-quality text-to-image (strong text rendering) for Apple Silicon. | |
| ## Usage | |
| ```bash | |
| mflux-generate-qwen --model OsaurusAI/Qwen-Image-mflux-4bit \ | |
| --prompt "a small red cube on a white table" --steps 20 | |
| ``` | |
| Or load in [Osaurus](https://osaurus.ai). | |
| ## Provenance | |
| - Base: [Qwen/Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) © Qwen — Apache-2.0 | |
| - Quantization: Osaurus · mflux 0.18 · 4-bit · eric@osaurus.ai | |