Skip to content
#

compressed-inference

Here is 1 public repository matching this topic...

Nexus ZLC is an experimental offline toolkit for lossless GGUF compression and compressed-weight inference. It preserves original model data, supports compatible models through a custom WebGPU engine, and includes restoration and before-and-after perplexity tests.

  • Updated Oct 10, 2026
  • HTML

Add this topic to your repo

To associate your repository with the compressed-inference topic, visit your repo's landing page and select "manage topics."

Learn more