blaizzy
0 Apps · 6 Tools · 1 Intel
Prince Canuma is a Poland-based ML engineer who worked at Neptune.ai on MLOps infrastructure before founding FastMLX, a production-grade API server for Apple's MLX framework, which was acquired by Arcee AI where he then served as an ML Research Engineer. He now works at Neywa Labs, specializing in on-device inference for large language, vision, and audio models on Apple Silicon.
Tools
A Python package for running and fine-tuning Vision Language Models (VLMs) locally on Mac with Apple Silicon using MLX. Supports multimodal inference with images, audio, and video, plus features like quantization and fine-tuning.
Modular Swift SDK for audio processing with MLX on Apple Silicon — TTS, STT, and audio analysis for iOS and macOS apps.
Run vision and language embedding models locally on Mac using MLX — fast on-device retrieval for Apple Silicon.
Swift bindings for espeak-ng — embed open-source text-to-speech directly in iOS and macOS apps without cloud round-trips.
Intel
Blaizzy's hands-on series for building LLMs from scratch — code-first walkthroughs of architecture, training, and inference.