---
library_name: mlx
license: apache-2.0
base_model: netflix/void-model
tags:
  - mlx
  - mlx-forge
  - apple-silicon
  - safetensors
  - quantized
  - int4
---

# dgrauet/void-model-mlx-q4

Int4 quantization (group_size 64, transformer Linear weights only) of
[dgrauet/void-model-mlx](https://huggingface.co/dgrauet/void-model-mlx), the MLX
conversion of [netflix/void-model](https://huggingface.co/netflix/void-model).

Quantized with [mlx-forge](https://github.com/dgrauet/mlx-forge)
(`mlx-forge convert void-model --quantize --bits 4`).

**This is the 32 GB configuration**: paired with the q8 base model, a full
two-pass BigBen run (30 steps, 13 frames, 352×624) peaks at ~23.7 GB —
under the 26.8 GB recommended working set of a 32 GB Apple Silicon Mac.
Quality vs the bf16 weights: PSNR ≈ 35.5 dB on the same seed.

## Usage

These weights can be used with [void-model-mlx](https://github.com/dgrauet/void-model-mlx):

```bash
python -m void_mlx.infer \
    --sample sample/BigBen \
    --pass1 weights/q4/void_pass1.safetensors \
    --pass2 weights/q4/void_pass2.safetensors \
    --base-model /path/to/CogVideoX-Fun-V1.5-5b-InP-mlx-q8 \
    --steps 30 --max-frames 13 --height 352 --width 624 \
    --output result.gif
```

Keep `quantize_config.json` next to the weights (the loader also infers
bits/group_size from the weight shapes if it is missing).

## Related Projects

- **void-model-mlx (inference):** https://github.com/dgrauet/void-model-mlx
- **VideoX-Fun-mlx (engine):** https://github.com/dgrauet/VideoX-Fun-mlx
- **Base model weights (q8):** https://huggingface.co/dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx-q8
- **bf16 variant:** https://huggingface.co/dgrauet/void-model-mlx
- **q8 variant:** https://huggingface.co/dgrauet/void-model-mlx-q8

## Files

- `config.json` (365.00 B)
- `quantize_config.json` (64.00 B)
- `split_model.json` (1.40 KB)
- `void_pass1.safetensors` (4.01 GB)
- `void_pass2.safetensors` (4.01 GB)