Instructions to use dgrauet/void-model-mlx-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dgrauet/void-model-mlx-q4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir void-model-mlx-q4 dgrauet/void-model-mlx-q4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Rename the build note key so it cannot collide with the per-component notes table
Browse files- split_model.json +1 -1
split_model.json
CHANGED
|
@@ -22,5 +22,5 @@
|
|
| 22 |
"q8 variant: https://huggingface.co/dgrauet/void-model-mlx-q8"
|
| 23 |
],
|
| 24 |
"cli_snippet": "python -m void_mlx.infer \\\n --sample sample/BigBen \\\n --pass1 weights/q4/void_pass1.safetensors \\\n --pass2 weights/q4/void_pass2.safetensors \\\n --base-model /path/to/CogVideoX-Fun-V1.5-5b-InP-mlx-q8 \\\n --steps 30 --max-frames 13 --height 352 --width 624 \\\n --output result.gif",
|
| 25 |
-
"
|
| 26 |
}
|
|
|
|
| 22 |
"q8 variant: https://huggingface.co/dgrauet/void-model-mlx-q8"
|
| 23 |
],
|
| 24 |
"cli_snippet": "python -m void_mlx.infer \\\n --sample sample/BigBen \\\n --pass1 weights/q4/void_pass1.safetensors \\\n --pass2 weights/q4/void_pass2.safetensors \\\n --base-model /path/to/CogVideoX-Fun-V1.5-5b-InP-mlx-q8 \\\n --steps 30 --max-frames 13 --height 352 --width 624 \\\n --output result.gif",
|
| 25 |
+
"build_note": "**This is the 32 GB configuration**: paired with the q8 base model, a full\ntwo-pass BigBen run (30 steps, 13 frames, 352\u00d7624) peaks at ~23.7 GB \u2014\nunder the 26.8 GB recommended working set of a 32 GB Apple Silicon Mac.\nQuality vs the bf16 weights: PSNR \u2248 35.5 dB on the same seed."
|
| 26 |
}
|