… Access to local inference I've written about inference snaps in the past and presented more detail at a recent AI Native Dev meetup , but the bottom line is that inference snaps provide simplified local access to inference with models that have been specifically optimised for your hardware. …
… It's a physical action layer connected to hundreds of integrations across your entire system: lights, audio, scenes, shortcuts, hardware, apps, automations. …
… Combined, these projects will create an estimated 90,000 jobs and help meet U.S. economic and national security goals. …
… There are highly specific Playbooks for generating images with ComfyUI and Z Image Turbo, running LLMs with ROCm, LM Studio: Chat, etc; advanced LLM use-cases on PyTorch with ROCm; local LLM-assisted software development with VS Code and Qwen3-Coder-30B; and workflow automation with n8n and GPT-OSS… …
… Home lab users will also find a good fit here, especially for those who want something compact for networking or automation projects, but still want standard x86 software compatibility. …
… Later this year, we will extend the Surface for Business portfolio with models featuring the Snapdragon X2 processors, delivering up to 80% faster local AI inferencing than before and uncompromising battery life. …