Downloads · 30 days
0
nunchaku-prebuilt-torch2.14-cu130
IrisLan/nunchaku-prebuilt-torch2.14-cu130
nunchaku-prebuilt-torch2.14-cu130 is a machine learning model from IrisLan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Binary mirror for the GitHub distribution project.
Access
Public
Updated Sep 14, 2026
Repo size
51.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.whl51.6 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026
- SHA
- d29aa5e7
Model card
From the Hugging Face model README
Nunchaku prebuilt — PyTorch 2.14 + CUDA 13.0
Binary mirror for the GitHub distribution project.
The file under rtx4090-sm89/ was compiled from Nunchaku commit 302e0e97024ebd68688fe890e5df83731edf7b54 with:
- Linux x86_64
- Python 3.12 (
cp312) - PyTorch 2.14.0+cu130
- CUDA toolkit 13.0.88
-gencode arch=compute_89,code=sm_89
It was installed and validated on a physical NVIDIA GeForce RTX 4090 by executing the AWQ GEMV CUDA kernel and synchronizing the device.
Wheel SHA-256:
b29d74fca0b6021bc80714e679c93278ce35ed57dfac657ff0bbb7d3a146ef91 nunchaku-1.3.0.dev20260914+cu13.0torch2.14-cp312-cp312-linux_x86_64.whl
Use the full installation and GPU compatibility instructions in the GitHub README. The RTX 5090 sm_120a build remains available separately in GitHub Release v1.0.0.
- License
- apache-2.0
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026