Tags: Apple Silicon

Ollama, a runtime for running large language models locally, announced preview support for Apple’s open‑source MLX framework and added Nvidia’s NVFP4 compression format. The update targets Apple Silicon Macs, requiring at least 32 GB of RAM, and currently supports Alibaba’s 35‑billion‑parameter Qwen 3.5 model. These changes aim to improve caching, memory efficiency, and overall speed, aligning with growing interest in running AI models on personal machines amid frustrations with cloud‑based rate limits and subscription costs. Weiterlesen

Modular, the AI‑hardware software startup founded by former Apple and Google engineers Chris Lattner and Tim Davis, announced a $250 million financing round. The company aims to create a unified software layer that lets developers run AI workloads across GPUs and CPUs from multiple vendors, including Nvidia, AMD and Apple Silicon. By providing a portable programming language and optimization tools, Modular seeks to reduce reliance on proprietary stacks such as Nvidia's CUDA and to broaden access to high‑performance compute for cloud providers and AI developers. Weiterlesen