Danmoreng

Linux & Powershell scripts to easily set up and run the Qwen 3.5 series locally on Windows and Linux with llama.cpp.

Mandelbrot explorer with vuejs and webgl.

A PowerShell script to fully automate the setup of `llama.cpp` on Windows. It installs all prerequisites, including the correct CUDA Toolkit and build tools, and compiles `llama.cpp` from the source.

Desktop app with Compose Multiplatform to use Qwen3-TTS with an UI.

No description.

Minimal local desktop app for preset-driven image generation with stable-diffusion.cpp, built with Kotlin Compose and a native C++ worker.

No description.

Local-first Android voice notes with live on-device transcription, transcript cleanup, titles, and summaries powered by Nemotron ASR and Gemma. Built with Jetpack Compose and Room.

Simple Android app implementing Qwen3 TTS

No description.

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Simple Direct3D 12 Windows based Mandelbrot viewer app.

No description.

qwen35x is a focused C++/CUDA inference engine for Qwen3.5 models, built for correctness-first bring-up and fast GPU decode. It includes a native tokenizer, CPU reference inference, CUDA-hybrid inference, and reproducible benchmark scripts.

LLM inference in C/C++

simple websearch mcp server to use with llama.cpp

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Highly optimized CUDA inference engine for 16 GB GPUs, targeting Blackwell first

No description.

Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.

No description.

Tensor library for machine learning

Port of Mistral's Voxtral model in C/C++

No description.

No description.

A desktop app to translate in-game chat using screenshots and the Gemini API.

No description.

onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime

No description.

No description.

No description.

No description.