Text-to-Image
MLX
MiniMax H3
Safetensors
English
apple-silicon
macos
image-to-image
image-editing
image-generation
Instructions to use devin-lai/MiniMax-H3-Image-mlx 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 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download devin-lai/MiniMax-H3-Image-mlx --local-dir MiniMax-H3-Image-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download reports/optimization-r3/embedding/rows-timed-2.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 1.7 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/reports/optimization-r3/embedding/rows-timed-2.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/reports/optimization-r3/embedding/rows-timed-2.json
-
curl -L -o rows-timed-2.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/reports/optimization-r3/embedding/rows-timed-2.json
1.7 kB
| { | |
| "mode": "rows", | |
| "seconds": 0.005294707836583257, | |
| "physical": { | |
| "sampled_peak_physical_bytes": 32211640, | |
| "lifetime_peak_physical_bytes": 32244408, | |
| "sample_interval_s": 0.001, | |
| "sample_count": 3, | |
| "scope": "Parent process only; includes Metal; excludes compiler XPC services. Counters overlap; do not sum." | |
| }, | |
| "mlx_peak_bytes": 901120, | |
| "output_sha256": "4acd76ed7d093f0a9c07c88a77295f93d7d20199b11a9a932707e321d2afbdbf", | |
| "shape": [ | |
| 88, | |
| 5120 | |
| ], | |
| "environment": { | |
| "platform": "macOS-27.0.1-arm64-arm-64bit", | |
| "machine": "arm64", | |
| "metal": { | |
| "device_name": "Apple M5 Pro", | |
| "max_recommended_working_set_size": 55662788608, | |
| "memory_size": 68719476736, | |
| "architecture": "applegpu_g17s", | |
| "max_buffer_length": 41747087360, | |
| "resource_limit": 499000 | |
| }, | |
| "versions": { | |
| "mlx": "0.32.4", | |
| "mlx-metal": "0.32.4", | |
| "numpy": "2.5.4", | |
| "safetensors": "0.8.0", | |
| "transformers": "4.57.6", | |
| "torch": "2.15.0", | |
| "Pillow": "13.0.0", | |
| "scikit-image": "0.26.0" | |
| }, | |
| "precision_environment": { | |
| "MLX_ENABLE_TF32": "0", | |
| "MLX_CONV_WINOGRAD": "0" | |
| } | |
| }, | |
| "scope": "Cold process, page-cache warm tensor read + gather only. Excludes tokenizer and full 50-layer encoder.", | |
| "outer_seconds": 0.09905358287505805, | |
| "repeat": 2, | |
| "phase": "timed", | |
| "command": [ | |
| "/Users/devin/Desktop/MiniMax-H3-Image-mlx/.venv/bin/python", | |
| "-m", | |
| "experiments.r3.embedding", | |
| "--encoder", | |
| "/Users/devin/Desktop/minimax-h3-image-opt/models/MiniMax-H3/text_encoder", | |
| "--mode", | |
| "rows", | |
| "--output", | |
| "reports/optimization-r3/embedding/rows-timed-2.json" | |
| ] | |
| } | |