Sponsored by Vmake Labs Video Enhancer
Toolify Toolify logo
AI Models
Wan2.2-TI2V-5B-mlx-q8

Anes1032 / Wan2.2-TI2V-5B-mlx-q8

Run on huggingface.co
huggingface.co
Total runs: 1.6K
24-hour runs: -156
7-day runs: 119
30-day runs: 568
Model's Last Updated: June 23 2026
image-to-video

Introduction of Wan2.2-TI2V-5B-mlx-q8

Model Details of Wan2.2-TI2V-5B-mlx-q8

Wan2.2-TI2V-5B — MLX 8-bit (q8)

MLX-format, 8-bit quantized conversion of Wan-AI/Wan2.2-TI2V-5B for native inference on Apple Silicon via 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) 
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 . This repository only quantizes and re-packages the weights for MLX; the model architecture and training are unchanged.

Runs of Anes1032 Wan2.2-TI2V-5B-mlx-q8 on huggingface.co

1.6K
Total runs
-156
24-hour runs
-58
3-day runs
119
7-day runs
568
30-day runs

More Information About Wan2.2-TI2V-5B-mlx-q8 huggingface.co Model

More Wan2.2-TI2V-5B-mlx-q8 license Visit here:

https://choosealicense.com/licenses/apache-2.0

Wan2.2-TI2V-5B-mlx-q8 huggingface.co

Wan2.2-TI2V-5B-mlx-q8 huggingface.co is an AI model on huggingface.co that provides Wan2.2-TI2V-5B-mlx-q8's model effect (), which can be used instantly with this Anes1032 Wan2.2-TI2V-5B-mlx-q8 model. huggingface.co supports a free trial of the Wan2.2-TI2V-5B-mlx-q8 model, and also provides paid use of the Wan2.2-TI2V-5B-mlx-q8. Support call Wan2.2-TI2V-5B-mlx-q8 model through api, including Node.js, Python, http.

Wan2.2-TI2V-5B-mlx-q8 huggingface.co Url

https://huggingface.co/Anes1032/Wan2.2-TI2V-5B-mlx-q8

Anes1032 Wan2.2-TI2V-5B-mlx-q8 online free

Wan2.2-TI2V-5B-mlx-q8 huggingface.co is an online trial and call api platform, which integrates Wan2.2-TI2V-5B-mlx-q8's modeling effects, including api services, and provides a free online trial of Wan2.2-TI2V-5B-mlx-q8, you can try Wan2.2-TI2V-5B-mlx-q8 online for free by clicking the link below.

Anes1032 Wan2.2-TI2V-5B-mlx-q8 online free url in huggingface.co:

https://huggingface.co/Anes1032/Wan2.2-TI2V-5B-mlx-q8

Wan2.2-TI2V-5B-mlx-q8 install

Wan2.2-TI2V-5B-mlx-q8 is an open source model from GitHub that offers a free installation service, and any user can find Wan2.2-TI2V-5B-mlx-q8 on GitHub to install. At the same time, huggingface.co provides the effect of Wan2.2-TI2V-5B-mlx-q8 install, users can directly use Wan2.2-TI2V-5B-mlx-q8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Wan2.2-TI2V-5B-mlx-q8 install url in huggingface.co:

https://huggingface.co/Anes1032/Wan2.2-TI2V-5B-mlx-q8

Url of Wan2.2-TI2V-5B-mlx-q8

Wan2.2-TI2V-5B-mlx-q8 huggingface.co Url

Provider of Wan2.2-TI2V-5B-mlx-q8 huggingface.co

Anes1032
ORGANIZATIONS
huggingface.co

Other API from Anes1032