Pinned Loading

1. llama.cpp-nvfp4-gemma4assist llama.cpp-nvfp4-gemma4assist Public

   Forked from ggml-org/llama.cpp

   llama.cpp fork: NVF4P quantize emitter + Gemma 4 31B Assistant speculative draft support - losslessly accelerate Gemma 4 31B at 128K context on a single 32GB Blackwell GPU

   C++

2. WindowsDriverExport WindowsDriverExport Public

   For exporting 3rd party Windows Drivers to use with Hiren's Boot CD & other backup/troubleshooting scenarios

   PowerShell

3. opencode-sync opencode-sync Public

   Keep opencode's model list in sync with your local vLLM or llama.cpp server

   Python

4. oddcode oddcode Public

   Odd bits and pieces

   PowerShell 3 2

5. ntfy-to-slack ntfy-to-slack Public

   Pushes messages received via Ntfy to a Slack webhook

   Go 5 7

6. tiktok-favvideo-downloader tiktok-favvideo-downloader Public

   Backup your favorite tiktok videos

   Go