| --- |
| license: apache-2.0 |
| base_model: Wan-AI/Wan2.2-T2V-A14B-Diffusers |
| pipeline_tag: text-to-video |
| library_name: mlx-gen |
| tags: |
| - mlx |
| - mlx-gen |
| - mflux |
| - apple-silicon |
| - bf16 |
| - wan |
| - wan2.2 |
| - video-generation |
| - text-to-video |
| - wan-a14b |
| --- |
| # wan2.2-t2v-a14b-diffusers-bf16 |
|
|
| This repository contains BF16 MLX-Gen saved weights for |
| [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers). |
| It is designed for local Apple Silicon inference with |
| [`mlx-gen`](https://github.com/lpalbou/mlx-gen). |
|
|
| It uses the mflux/MLX saved-weight layout. It is not a Diffusers or Transformers |
| `from_pretrained()` checkpoint. |
|
|
| ## Source Model |
|
|
| Original model: [`Wan-AI/Wan2.2-T2V-A14B-Diffusers`](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers). |
|
|
| This prepared derivative follows the Apache 2.0 license of the source model. |
|
|
| ## Precision |
|
|
| This package stores the Wan A14B T2V transformer and VAE weights for MLX-Gen BF16 runtime use. The UMT5 text encoder, scheduler metadata, tokenizer files, and model index are included in the prepared folder. |
|
|
| ## Validation |
|
|
| Measured on 2026-06-04 with `mlx-gen 0.18.9` on Apple Silicon. The upstream Diffusers source snapshot measured about 118 GiB in the local Hugging Face cache before preparing these packages. The table below reports prepared-package generation from model init through MP4 save and post-save video-health validation. |
|
|
| Validation profile: `384x224`, 33 frames, 12 denoising steps, guidance `4`, guidance-2 `3`, 8 fps, seed `4242`, `--low-ram`. |
|
|
| | Package | Disk | Full-Process Physical Peak | Max RSS | MLX Peak | Total Time | Video Health | |
| |---|---:|---:|---:|---:|---:|---| |
| | This BF16 package | 64.3 GiB | 33.0 GiB | 31.8 GiB | 27.7 GiB | 152.7 s | 33/33 frames, 384x224, 8 fps, temporal delta 1.3 | |
| | Mixed q8/BF16 package | 39.7 GiB | 20.7 GiB | 19.5 GiB | 15.5 GiB | 154.8 s | 33/33 frames, 384x224, 8 fps, temporal delta 1.4 | |
|
|
| Physical peak is Darwin `ri_phys_footprint` sampled for the full process. The validation is intentionally small and repeatable; it is not a claim that every full-size `1280x720`, 81-frame, 40-step job has the same memory or timing profile. |
|
|
| ## Usage |
|
|
| ```bash |
| python -m pip install -U mlx-gen |
| |
| mlxgen download --model AbstractFramework/wan2.2-t2v-a14b-diffusers-bf16 |
| |
| mlxgen generate \ |
| --model AbstractFramework/wan2.2-t2v-a14b-diffusers-bf16 \ |
| --task text-to-video \ |
| --prompt "A cinematic scene of a scientist working on agentic AI through the night, monitors glowing, papers shifting in a slow dolly shot." \ |
| --width 384 \ |
| --height 224 \ |
| --frames 33 \ |
| --steps 12 \ |
| --guidance 4 \ |
| --guidance-2 3 \ |
| --fps 8 \ |
| --seed 4242 \ |
| --low-ram \ |
| --metadata \ |
| --output video.mp4 |
| ``` |
|
|
| ## Compatibility |
|
|
| Requires `mlx-gen >= 0.18.9`. |
|
|
| Generated with `mlx-gen 0.18.9`. |
|
|
| Use the `mlxgen` command and Python import path for new MLX-Gen projects. |
|
|
| ## Attribution |
|
|
| MLX-Gen is based on [mflux](https://github.com/filipstrand/mflux) by Filip Strand and the original mflux contributors. |
|
|
| Prepared and contributed by [@lpalbou](https://huggingface.co/lpalbou). |
|
|
