A nice new technology #5547
zhaoqi571436204
started this conversation in
Ideas
Replies: 1 comment
-
@comfyanonymous please will this be implemented in the ComfyUI?🙏 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
https://github.com/mit-han-lab/nunchaku
https://huggingface.co/mit-han-lab/svdquant-models
VDQuant is a post-training quantization technique for 4-bit weights and activations that well maintains visual fidelity. On 12B FLUX.1-dev, it achieves 3.6× memory reduction compared to the BF16 model. By eliminating CPU offloading, it offers 8.7× speedup over the 16-bit model when on a 16GB laptop 4090 GPU, 3× faster than the NF4 W4A16 baseline. O
Beta Was this translation helpful? Give feedback.
All reactions