GoKawiil
Tech News
Nvidia has released PAIR (Personal AI Router) in open beta on GitHub, a system that lets users split GPU-intensive AI agent workloads into parallel subtasks and offload them to other computers on the same local network. The software works across Windows, Mac and Linux, uses mDNS for device discovery and MTLS for security, and currently supports the Ollama and LM Studio model engines.
A developer detailed a personal setup running local language models on an Apple M4 Pro Mac mini, using Qwen and Gemma models served through an inference tool called oMLX, connected across devices via Tailscale. The setup powers an agent backend called Hermes plus various chat and coding tools, and reportedly takes about 30 minutes to configure.
Apple has released a new Mac mini lineup powered by its M6 chip and M5 Pro chip, replacing the previous M4 and M4 Pro models. The M6, built on a 2nm process, brings a 12-core CPU, 12-core GPU, and dual 16-core Neural Engine, while the M5 Pro offers up to an 18-core CPU and 20-core GPU. Both versions also gain higher memory bandwidth and increased maximum RAM configurations.