Qwen3.8-Flash-Next on any consumer hardware
Extract hardcoded subtitles from videos via a simple GUI
A GPU-accelerated library containing highly optimized building blocks
HeavyDB (formerly MapD/OmniSciDB)
CV-CUDA™ is an open-source, GPU accelerated library
Open Source Computer Vision Library
VoiceStudio is the open-source, fully-local ElevenLabs alternative
Relax! Flux is the ML library that doesn't make you tensor
HunyuanVideo: A Systematic Framework For Large Video Generation Model
ArrayFire, a general purpose GPU library
Solve puzzles. Learn CUDA
Open Source Differentiable Computer Vision Library
Cross platform .Net wrapper to the OpenCV image processing library
ProtoMotions is a GPU-accelerated simulation and learning framework
ReFT: Representation Finetuning for Language Models
Standardized Serverless ML Inference Platform on Kubernetes
Making large AI models cheaper, faster and more accessible
Open source voice dictation technology
Toolkit for conversational AI
High-speed Large Language Model Serving for Local Deployment
Please do not feed the models
Voice Recognition to Text Tool
Running large language models on a single GPU
Extract and convert data from any document, images, pdfs, word doc
Easily compute clip embeddings and build a clip retrieval system