MLX
Tag125 stories
MLX news and updates covering Apple's open-source array framework for machine learning on Apple silicon. Readers can learn about running and fine-tuning LLMs locally on Macs, quantized models, unified memory performance and MLX-based inference engines.
PyTorch and MLX for Apple SiliconWeekly AI and NLP News — January 15th 2024Whisper: Nvidia RTX 4090 vs M1Pro with MLX (updated with M2/M3)The Hadamard Transform Bug That Quietly Made Our Inverse Worse Than Returning ZerosThe PR you would have opened yourselfMy thousand dollar iPhone can't do mathMeasuring Model Quantisation Quality with KL Divergenceollama 0.14 Can Make Use Of Bash For Letting AI/LLMs Run Commands On Your SystemTrying out Qwen3 Coder Flash using LM Studio and Open WebUI and LLMLocal AI Models with LM Studio and Spring AI