Instructions to use devin-lai/MiniMax-H3-Image-mlx-shared with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use devin-lai/MiniMax-H3-Image-mlx-shared with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download devin-lai/MiniMax-H3-Image-mlx-shared --local-dir MiniMax-H3-Image-mlx-shared
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download README.md from devin-lai/MiniMax-H3-Image-mlx-shared: direct link, hf CLI and curl.
- Browser
- Download file 2.59 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx-shared/resolve/main/README.md
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx-shared/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx-shared/resolve/main/README.md
library_name: mlx
pipeline_tag: text-to-image
license: other
license_name: minimax-h3-image-community-license-agreement
license_link: LICENSE
base_model: MiniMaxAI/MiniMax-H3-Image
language:
- en
inference: false
tags:
- mlx
- apple-silicon
- macos
- minimax-h3
- image-generation
- image-editing
- image-to-image
- safetensors
extra_gated_heading: Request access under the MiniMax license
extra_gated_description: >-
Manual review. Read LICENSE and the territorial, commercial and acceptable-use
conditions before requesting access.
extra_gated_fields:
Country of use: country
I accept the MiniMax-H3-Image Community License Agreement including Exhibit A: checkbox
I am authorized to receive and use these materials in my territory: checkbox
extra_gated_eu_disallowed: true
MiniMax H3 Image MLX 路 shared components
Shared VAE, PDD heads, native support tensors, transformer configuration and evaluated six-step modulation tables for the community MLX port by Devin Lai. Powered by MiniMax-H3-Image.
The main runtime downloads these components once and reuses them
across BF16, lossless packed BF16, Q8 and Q4. It omits the redundant native
support file for the original BF16 variant. No other variant weights are
stored here. The separate native text encoder is fetched from its pinned
official MiniMaxAI/MiniMax-H3 repository and retains its own license.
Use h3-mlx download --variant packed12 --model-dir models/packed12 after
installation. Frozen modulation tables retain the six original timesteps and
the editing anchor; the loader validates MLX 0.32.4, strict FP32 settings and
the original schedule. Format and modifications.
Shared model files: 3.86 GiB. Download them once and reuse them across variants. The BF16 downloader skips the redundant native-support copy; the separate upstream text encoder is roughly 62 GiB. These are download sizes, not RAM requirements.
This is an inference distribution, not a newly trained model. Training provenance, biases and limitations remain those of the upstream model. The MiniMax-H3-Image Community License Agreement, territorial, commercial and acceptable-use conditions apply. The standard grant excludes the EU, UK, Republic of Korea and US. Manual access review does not grant additional rights. NOTICE.
Release: v0.4.1 (v0.4.0 weights with download-count metadata). Access requests are reviewed manually. Main release status.