Instructions to use mflux-community/moss-image-sft-mflux-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- mflux
How to use mflux-community/moss-image-sft-mflux-bf16 with mflux:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- MLX
How to use mflux-community/moss-image-sft-mflux-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mflux-community/moss-image-sft-mflux-bf16 --local-dir moss-image-sft-mflux-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download README.md from mflux-community/moss-image-sft-mflux-bf16: direct link, hf CLI and curl.
- Browser
- Download file 2.88 kB
-
https://huggingface.co/mflux-community/moss-image-sft-mflux-bf16/resolve/main/README.md
- Command line
-
hf download hf://mflux-community/moss-image-sft-mflux-bf16/README.md
-
curl -L -o README.md https://huggingface.co/mflux-community/moss-image-sft-mflux-bf16/resolve/main/README.md
license: apache-2.0
base_model: OpenMOSS-Team/MOSS-Image-SFT
base_model_relation: quantized
pipeline_tag: text-to-image
library_name: mflux
tags:
- mflux
- mlx
- apple-silicon
- text-to-image
- moss-image
MOSS-Image-SFT 路 MFlux BF16
This is a BF16 MFlux version of MOSS-Image-SFT.
MFlux runs the latest state-of-the-art generative image models locally on your Mac in native MLX. MFlux is open source and free.
Community conversion by MFlux-Community -- not an official release from the original model's authors. The original model's license applies unchanged, see License.
MFlux versions of MOSS-Image-SFT
| QUANT | GB | Repo |
|---|---|---|
| BF16 | 26.2 | this repo |
| Q8 | 14.0 | mflux-community/moss-image-sft-mflux-q8 |
| Q6 | 10.7 | mflux-community/moss-image-sft-mflux-q6 |
| Q5 | 9.1 | mflux-community/moss-image-sft-mflux-q5 |
| Q4 | 7.5 | mflux-community/moss-image-sft-mflux-q4 |
| Q3 | 5.8 | mflux-community/moss-image-sft-mflux-q3 |
Converted on 2026-10-22.
BF16 is the full-precision MLX build -- no quantization. Use it as the highest-fidelity reference, or pass --quantize to quantize on the fly.
Usage
Install MFlux
uv tool install --upgrade mflux
Generate an image using MOSS-Image-SFT BF16:
mflux-generate-moss-image \
--model mflux-community/moss-image-sft-mflux-bf16 \
--base-model moss-image-sft \
--prompt "A wooden signpost in a forest reading HELLO WORLD" \
--width 768 \
--height 768 \
--seed 42 \
--output image.png
The weights are downloaded from this repo on first use. To keep a local copy instead:
hf download mflux-community/moss-image-sft-mflux-bf16 --local-dir ./moss-image-sft-mflux-bf16
then pass --model ./moss-image-sft-mflux-bf16.
License
This repo inherits the license of the original model: Apache 2.0. See the original model card for the full terms and any usage restrictions. The weights here were modified from the original release only by conversion to MLX.
Credits
- Original model: OpenMOSS-Team/MOSS-Image-SFT
- MLX implementation: MFlux by Filip Strand and contributors
- Conversion: MFlux-Community