| --- |
| license: other |
| license_name: minimax-h3-community-license-agreement |
| license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE |
| base_model: |
| - MiniMaxAI/MiniMax-H3 |
| base_model_relation: quantized |
| language: |
| - en |
| - zh |
| pipeline_tag: image-text-to-video |
| tags: |
| - fp8 |
| - int8 |
| - quantized |
| - text-to-video |
| - image-to-video |
| - video-generation |
| - unsloth |
| --- |
| |
| # MiniMax-H3, FP8 and INT8 |
|
|
| Pre-quantized PyTorch checkpoints of |
| [MiniMaxAI/MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3), for diffusers plus torchao. |
|
|
| MiniMax H3 is an omni-modal generative system that produces video with native stereo audio, up to |
| 15 seconds at 24 FPS with 32 kHz stereo audio. The files here quantize the `fl2va_pruned` |
| H3-Base first-and-last-frame variant, which takes zero, one or two input images plus text, and the |
| `ref2va_pruned` omni-reference variant, which takes a prompt plus up to twelve image, video and |
| audio references. Both schemes quantize the same 200 main-block matmuls, 95.8% of the parameters, |
| and leave every 1-D gain, every bias and the whole modulation path bit-identical. |
|
|
| ## Examples |
|
|
| Same prompt, same seed, same settings, one clip per checkpoint. 960x544, 124 frames, 24 FPS, |
| 8 steps, guidance 1.0, seed 11, on a single card. |
|
|
| > a red panda stepping along a mossy log in a misty forest, cinematic |
|
|
| | INT8 | FP8 | |
| |---|---| |
| | <img src="assets/h3_int8.gif" width="380"> | <img src="assets/h3_fp8.gif" width="380"> | |
|
|
| The GIFs are downsampled and silent. For the full 960x544 clips with their native 32 kHz stereo |
| audio track, play |
| [`assets/h3_int8.mp4`](https://huggingface.co/unsloth/MiniMax-H3-FP8/blob/main/assets/h3_int8.mp4) |
| and |
| [`assets/h3_fp8.mp4`](https://huggingface.co/unsloth/MiniMax-H3-FP8/blob/main/assets/h3_fp8.mp4). |
| H3 generates the audio jointly with the video, so the audio is part of the model output rather |
| than something added afterwards. |
|
|
| Stills from other prompts, three per format: |
|
|
| INT8 |
|
|
| <img src="samples/int8_1.png" width="260"> <img src="samples/int8_2.png" width="260"> <img src="samples/int8_3.png" width="260"> |
|
|
| FP8 |
|
|
| <img src="samples/fp8_1.png" width="260"> <img src="samples/fp8_2.png" width="260"> <img src="samples/fp8_3.png" width="260"> |
|
|
| ## Files |
|
|
| H3 ships two denoiser partitions and a load opens exactly one. `transformer/` serves the keyframe |
| workflow `fl2va`, which also covers text-only generation; `transformer_ref/` serves the |
| omni-reference workflow `ref2va`. They are separate weights, so each partition has its own |
| checkpoints here and the two sets are not interchangeable. |
|
|
| Keyframe and text-only (`fl2va`, from `transformer/`): |
|
|
| | File | Size | |
| |---|---| |
| | `MiniMax-H3-INT8.pt` | 18.86 GiB | |
| | `MiniMax-H3-INT8-ConvRot.pt` | 18.86 GiB | |
| | `MiniMax-H3-FP8.pt` | 18.87 GiB | |
|
|
| Omni-reference (`ref2va`, from `transformer_ref/`): |
|
|
| | File | Size | |
| |---|---| |
| | `MiniMax-H3-Ref2VA-INT8-ConvRot.pt` | 18.86 GiB | |
| | `MiniMax-H3-Ref2VA-FP8.pt` | 18.87 GiB | |
|
|
| **Every checkpoint lives here, INT8 included.** One repo on purpose: these are one artifact built |
| a few ways, and a loader picks between them by filename. Against the 40.23 GB bf16 pruned source |
| any of them takes the checkpoint to 20.25 GB and the end-to-end render peak from 57.11 GB to |
| 36.97 GB. Prefer INT8 with `torch.compile` and FP8 without it. |
|
|
| Pick the pair that matches the workflow you are running. The two partitions have the same class, |
| the same config and the same 635-key state dict, so a keyframe checkpoint seeded into the |
| reference workflow loads cleanly, passes every metadata check and generates from the wrong |
| weights rather than failing. The `Ref2VA` in the filename is the only thing that distinguishes |
| them. |
|
|
| The `-ConvRot` INT8 files store their weights in a Hadamard-rotated basis and need a loader that |
| rotates the activations to match; they carry a format tag that makes an older loader refuse them |
| rather than read them as plain INT8. Where both an INT8 and an INT8-ConvRot file exist, the |
| ConvRot one is the newer build. |
|
|
| ### Reference (Ref2VA) build recipe |
|
|
| Identical to the keyframe rungs apart from the source file: 313 Linears quantized, 55 skipped, the |
| `adaLN` modulation path left at full precision, and on the INT8 arm a ConvRot Hadamard rotation at |
| group size 256 over all 313. The source is |
| `minimax_h3_ref2va_pruned_bf16.safetensors` from |
| [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3), which is the reference |
| partition with the same curve-form modulation pruning as the keyframe one, and both files record |
| it in `metadata.base_checkpoint`. |
|
|
| Verified before publishing: each file loads through the pre-quantized path against the |
| `transformer_ref` config with no missing or unexpected keys, and renders a 640x384, 124-frame |
| reference clip. Measured against the reference-partition bfloat16 denoiser at the same prompt, |
| seed and shape (20 steps, two prompts, one image reference), the same composition comes back with |
| fine detail redistributed: SSIM 0.92 and 0.82 for INT8 and 0.88 and 0.78 for FP8, against a |
| determinism ceiling of 1.00 for the bfloat16 arm rendered twice. Those numbers are a divergence |
| measure, not a quality score. |
|
|
| Both are torchao pre-quantized transformer state dicts, per-output-channel absmax scales, INT8 |
| symmetric and FP8 e4m3. The skeleton is built on `meta` and the quantized subclass tensors are |
| assigned rather than copied, so dense bf16 never touches the GPU. Each file carries |
| `base_model_id = MiniMaxAI/MiniMax-H3` and a `base_checkpoint` naming the exact source it was cut |
| from (`.../minimax_h3_fl2va_pruned_bf16.safetensors` or |
| `.../minimax_h3_ref2va_pruned_bf16.safetensors`) in its metadata, which the loader checks before |
| accepting it. |
|
|
| The keyframe source is `minimax_h3_fl2va_pruned_bf16.safetensors` from |
| [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3), which already has the |
| modulation pruned to `[96768, 8]` per block plus a shared `adaln_t_table [1025, 8]`. Note that |
| stable-diffusion.cpp cannot load these, it has no int8 linear path that reads external per-channel |
| scales, so for sd.cpp use |
| [unsloth/MiniMax-H3-GGUF](https://huggingface.co/unsloth/MiniMax-H3-GGUF) instead. |
|
|
| ## Licence |
|
|
| MiniMax H3 Community License Agreement, from MiniMax-H3. Full text in |
| [`LICENSE`](https://huggingface.co/unsloth/MiniMax-H3-FP8/blob/main/LICENSE). Read it before use: |
| it defines an Applicable Territory and excludes some jurisdictions from it. MiniMax also publish a |
| [Q&A about the licence](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/QA-about-License.md). |
|
|
| These files are Model Derivatives, not a plain copy: the transformer is quantized and its |
| modulation is pruned, both of which change the numerics. Section III of the licence wants that |
| stated, so [`NOTICE`](https://huggingface.co/unsloth/MiniMax-H3-FP8/blob/main/NOTICE) lists every |
| change along with the attribution. Not an official MiniMax product, and not endorsed by MiniMax. |
|
|
