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 comparisons/optimization-v2/fp32-reference/trials.json from devin-lai/MiniMax-H3-Image-mlx: direct link, hf CLI and curl.
- Browser
- Download file 2.4 kB
-
https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/fp32-reference/trials.json
- Command line
-
hf download hf://devin-lai/MiniMax-H3-Image-mlx/comparisons/optimization-v2/fp32-reference/trials.json
-
curl -L -o trials.json https://huggingface.co/devin-lai/MiniMax-H3-Image-mlx/resolve/main/comparisons/optimization-v2/fp32-reference/trials.json
2.4 kB
| { | |
| "source_trace": "outputs/suite/product/native-3.trace.safetensors", | |
| "scope": "Same final latent, decoder-only hot latency", | |
| "trials": [ | |
| { | |
| "variant": "fp32-b4-compiled", | |
| "median_ms": 5210.008415859193, | |
| "min_ms": 5210.008415859193, | |
| "max_ms": 5210.008415859193, | |
| "samples_ms": [ | |
| 5210.008415859193 | |
| ], | |
| "pixel_identical": true, | |
| "mae_8bit": 0.0, | |
| "max_error_8bit": 0, | |
| "psnr_db": null, | |
| "ssim_rgb": 1.0 | |
| }, | |
| { | |
| "variant": "native-b1", | |
| "median_ms": 4797.312458977103, | |
| "min_ms": 4797.312458977103, | |
| "max_ms": 4797.312458977103, | |
| "samples_ms": [ | |
| 4797.312458977103 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.5589210987091064, | |
| "max_error_8bit": 16, | |
| "psnr_db": 49.78516664658046, | |
| "ssim_rgb": 0.9966293860246318 | |
| }, | |
| { | |
| "variant": "native-b4", | |
| "median_ms": 2059.1762911062688, | |
| "min_ms": 2059.1762911062688, | |
| "max_ms": 2059.1762911062688, | |
| "samples_ms": [ | |
| 2059.1762911062688 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.5589210987091064, | |
| "max_error_8bit": 16, | |
| "psnr_db": 49.78516664658046, | |
| "ssim_rgb": 0.9966293860246318 | |
| }, | |
| { | |
| "variant": "compiled-b4", | |
| "median_ms": 1683.8960419408977, | |
| "min_ms": 1683.8960419408977, | |
| "max_ms": 1683.8960419408977, | |
| "samples_ms": [ | |
| 1683.8960419408977 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.5589210987091064, | |
| "max_error_8bit": 16, | |
| "psnr_db": 49.78516664658046, | |
| "ssim_rgb": 0.9966293860246318 | |
| }, | |
| { | |
| "variant": "native-b8", | |
| "median_ms": 2054.585292004049, | |
| "min_ms": 2054.585292004049, | |
| "max_ms": 2054.585292004049, | |
| "samples_ms": [ | |
| 2054.585292004049 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.5588849385579427, | |
| "max_error_8bit": 16, | |
| "psnr_db": 49.786187719649895, | |
| "ssim_rgb": 0.9966299016185887 | |
| }, | |
| { | |
| "variant": "compiled-b8", | |
| "median_ms": 1655.5352921131998, | |
| "min_ms": 1655.5352921131998, | |
| "max_ms": 1655.5352921131998, | |
| "samples_ms": [ | |
| 1655.5352921131998 | |
| ], | |
| "pixel_identical": false, | |
| "mae_8bit": 0.5588849385579427, | |
| "max_error_8bit": 16, | |
| "psnr_db": 49.786187719649895, | |
| "ssim_rgb": 0.9966299016185887 | |
| } | |
| ] | |
| } | |