Instructions to use unsloth/MiniMax-H3-Image-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- Unsloth Desktop
Download NOTICE from unsloth/MiniMax-H3-Image-FP8: direct link, hf CLI and curl.
- Browser
- Download file 2.29 kB
-
https://huggingface.co/unsloth/MiniMax-H3-Image-FP8/resolve/main/NOTICE
- Command line
-
hf download hf://unsloth/MiniMax-H3-Image-FP8/NOTICE
-
curl -L -o NOTICE https://huggingface.co/unsloth/MiniMax-H3-Image-FP8/resolve/main/NOTICE
2.29 kB
| unsloth/MiniMax-H3-Image-FP8 | |
| "MiniMax-H3-Image is licensed under the MiniMax-H3-Image Community License Agreement, | |
| Copyright © 2026 MiniMax. All Rights Reserved." | |
| The weights here derive from MiniMax-H3-Image | |
| (https://huggingface.co/MiniMaxAI/MiniMax-H3-Image). | |
| LICENSE is the text MiniMax ships at | |
| https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/blob/main/LICENSE, verbatim. | |
| Modified files and the changes made to them (MiniMax-H3-Image Community License | |
| Agreement, Section III.2). Both files start from | |
| minimax_h3_image_pruned_bf16.safetensors as published by Comfy-Org | |
| (https://huggingface.co/Comfy-Org/MiniMax-H3-Image), which is the MiniMax-H3-Image | |
| diffusion transformer with the dense adaLN modulation projection replaced by a | |
| curve-form factorization of the time-embedding curve. That pruning is Comfy-Org's | |
| work and not Unsloth's. It changes the modulation numerics: at the 6 sampling steps | |
| the curve-form adaLN output differs from the dense release adaLN by a relative error | |
| of 6.5e-4 to 7.5e-4 (cosine 0.9999998). | |
| * MiniMax-H3-Image-INT8-ConvRot.safetensors: 313 Linear weights quantized to | |
| signed 8-bit integers with per-output-channel absmax scales, after a ConvRot | |
| block-Hadamard rotation at group size 256 applied to all 313, so the weights are | |
| stored in a rotated basis. This changes the numerics. proj_in, the curve table, | |
| norm_out.linear and the adaLN path are kept in fp32. Every other tensor is copied | |
| through bit-identical at its source precision. | |
| * MiniMax-H3-Image-FP8.safetensors: the same 313 Linear weights quantized to | |
| float8 e4m3 with per-output-channel absmax scales, which changes the numerics. | |
| No rotation is applied. proj_in, the curve table, norm_out.linear and the adaLN | |
| path are kept in fp32. Every other tensor is copied through bit-identical at its | |
| source precision. | |
| Both files also carry the per-step output heads from the release's | |
| pdd_fused_heads.safetensors, stored under the names pdd_proj_out.0 to pdd_proj_out.5 | |
| in fp32 with their values unchanged; only the tensor names and the container differ. | |
| Both are serialized as safetensors, with metadata recording the model family, the | |
| base model id and the base and heads revisions. | |
| Not an official MiniMax or Comfy-Org product, and not endorsed by either. | |