AIC++★ 795⑂ 105 forksApache-2.0
nace-ai/kapitsa
Apple Silicon LLM Inference Engine
High-performance inference engine optimized for Apple Silicon, supporting Qwen, Nemotron, and Flint models with OpenAI and Anthropic API compatibility.
// KEY FEATURES
- Runs Qwen, Nemotron, and Flint models natively on Apple Silicon
- Drop-in replacement for OpenAI and Anthropic API endpoints
- Written in C++ for maximum Metal GPU performance
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram