---
license: apache-2.0
base_model:
  - Wan-AI/Wan2.2-TI2V-5B
tags:
  - mlx
  - apple-silicon
  - video-generation
  - image-to-video
  - text-to-video
  - wan2.2
  - quantized
library_name: mlx-video
pipeline_tag: image-to-video
---

# Wan2.2-TI2V-5B — MLX 8-bit (q8)

MLX-format, **8-bit quantized** conversion of [Wan-AI/Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B)
for native inference on Apple Silicon via [mlx-video](https://github.com/Blaizzy/mlx-video).

TI2V-5B is the single-model (5B) Text+Image-to-Video variant of Wan2.2, using the
Wan2.2 VAE (`z_dim=48`). It runs comfortably at **720p (1280×704), 24fps** on a
64 GB Apple Silicon machine, where the heavier 14B dual-model (I2V-A14B) struggles.

## Contents

| File | Size | Notes |
|------|------|-------|
| `model.safetensors` | ~5 GB | Transformer (8-bit, group_size=64) |
| `t5_encoder.safetensors` | ~11 GB | UMT5-XXL text encoder (bf16) |
| `vae.safetensors` | ~2.6 GB | Wan2.2 VAE (z_dim=48, fp32) |
| `config.json` | — | Includes quantization metadata |

Total ≈ 18 GB.

## Quantization

- **8-bit, group_size=64**, applied to transformer Linear layers (self/cross-attention
  Q/K/V/O + FFN). Embeddings, norms, and the output head remain bf16.
- Converted with `mlx_video.models.wan_2.convert --quantize --bits 8 --group-size 64`.

## Usage (mlx-video)

```bash
pip install git+https://github.com/Blaizzy/mlx-video.git
# or: uv pip install git+https://github.com/Blaizzy/mlx-video.git

huggingface-cli download <THIS_REPO_ID> --local-dir ./Wan2.2-TI2V-5B-MLX-Q8

python -m mlx_video.models.wan_2.generate \
  --model-dir ./Wan2.2-TI2V-5B-MLX-Q8 \
  --image ./start.png \
  --prompt "the subject waves hello, warm sunlight, film grain" \
  --width 1280 --height 704 --num-frames 81 \
  --steps 40 --guide-scale 5.0 \
  --output-path out.mp4
```

- Resolution must be divisible by **32**. Frame count must be `4n+1`. Output is **24 fps**.
- `--image` is optional (TI2V also does pure text-to-video).

## Hardware

Validated on an Apple Silicon Mac (64 GB unified memory): 720p × 41 frames × 20 steps
≈ 15 min, stable memory. 32 GB+ recommended.

## License & Attribution

This is a derivative of **Wan-AI/Wan2.2-TI2V-5B**, released under **Apache-2.0**.
The Apache-2.0 license and `NOTICE` are included. All credit for the base model goes
to the Wan-AI / Alibaba team. MLX conversion via Prince Canuma's
[mlx-video](https://github.com/Blaizzy/mlx-video). This repository only **quantizes and
re-packages** the weights for MLX; the model architecture and training are unchanged.