Apple @ Work: The spiritual successor to the Xserve is here, thanks to Apple silicon and MLX

Apple @ Work is exclusively brought to you by Mosyle, the only Apple Unified Platform. Mosyle is the only solution that integrates in a single professional grade platform all the solutions necessary to seamlessly and automatically deploy, manage, and protect Apple devices at work. Over 45,000 organizations trust Mosyle to make millions of Apple devices work ready with no effort and at an affordable cost. Request your EXTENDED TRIAL today and understand why Mosyle is everything you need to work with Apple. I’ve spent the past few weeks thinking about how Apple built up the best deal in enterprise AI. Two things happened that make me think Apple knew that all along (or maybe they didn’t and got lucky). Meta released its most capable open-weight model yet and optimized it to run on a Mac Studio. I also spent time with Osaurus, an app that runs a usable local AI model on something as small as a 16 GB Apple silicon laptop without needing a network connection. They even have two models that will run on 8 GB. The Xserve has been dead since 2011, but its spiritual successor sits on a desk rather than in a rack. About Apple @ Work: Bradley Chambers has been an Apple IT admin since 2009. Through his experience deploying and managing firewalls, switches, a mobile device management system, enterprise grade WiFi, 1000s of Macs, and 1000s of iPads, Bradley will highlight ways in which Apple IT managers deploy Apple devices, build networks to support them, train users, share stories from the trenches of IT management, and ways Apple could improve its products for IT departments. For the last few years, the narrative has been that Apple fell behind in AI because it didn’t have a frontier model. Siri AI got delayed, and the Apple Intelligence rollout was not great. In hindsight, I think Apple was right not to run that race, as the frontier-model business has turned into somewhat of a capital bonfire. Every frontier lab is spending billions on GPUs to be the best for a few months at a time, and the moment a model is good enough, someone else releases an open-weight version that runs on hardware you already own. Open-weight models prove it: Muse Spark Open has 816 billion parameters, 42 billion active parameters, and a million-token context window, and Meta is giving it away. Apple didn’t build that LLM. It built the hardware that runs it. With that being said, Siri is still far behind. Apple built the infrastructure for everything but the frontier model Look at what Apple has shipped while everyone was waiting on them to try to compete with Anthropic or OpenAI. With Apple silicon’s unified memory, the GPU can use up to 512 GB of memory on a single Mac Studio, instead of being limited to whatever fits on a graphics card. MLX is Apple’s machine learning framework, and it’s built specifically for the unified memory architecture of Apple silicon. If you’ve used NumPy, the API will feel familiar right away. On top of that, MLX includes higher-level packages for neural networks and optimizers, along with function transformations for automatic differentiation and graph optimization, so you can build more complex models without giving up efficiency. It also has bindings in Swift, C++, and C, which means it runs on any Apple platform. Apple’s own Machine Learning Research post shows four M5 Ultra Mac Studios running Muse Spark Open at over 36 tokens per second, which is faster than you can read, while peaking around 300 watts per machine. Meta’s own words on the setup: Apple’s unified memory architecture lets the M5 Ultra’s integrated GPU use up to 512 GB per Mac Studio, so two machines can hold an entire model. And the chip’s 1.2 TB/s of memory bandwidth is fast enough to read the small slice each token needs. The result is two Mac Studios behave like one supercomputer with a terabyte of unified memory. We tested a range of agentic workflows running entirely on-device, using Muse Code powered by Muse Spark Open, including shipping real iOS changes to Ice Cubes (an open-source Mastodon client) — bug fixes, new features, full build — and driving DaVinci Resolve end to end, with the model reviewing footage frame by frame to find the strongest moments and crop them vertically. That’s the Xserve pitch, rebuilt for 2026. Apple killed the Xserve in 2011 because nobody wanted a Mac in a data center. The Mac mini came along and provided some new use cases over the years. Now, a couple of Mac Studios can host a model that would otherwise require a rack of Nvidia hardware and a power budget to match, and it does so quietly enough to sit under a desk. Apple wasn’t trying to compete with OpenAI, Anthropic, or Nvidia. It was building the infrastructure for everything except the frontier model, and it looks like that’s where the market is going. A company like MacStadium has to be loving this future as well. It works on a 16 GB MacBook too The Mac Studio story is the headline, but what matters most to most IT teams is at the other end of the lineup. I had Terence Pae, co-founder and CEO of Osaurus, on the Apple @ Work podcast last week. Osaurus is a free, open-source AI tool for the Mac. It helps manage local models that work offline, but it can also call a frontier model when needed. A really cool feature, when it does this, is that Osaurus runs a small local model first to find names, phone numbers, and account numbers in whatever you pasted, and swaps them for placeholders before anything goes to Claude or OpenAI. Osaurus has no servers and no customer database. If the company went out of business tomorrow, the app would keep running until macOS broke it. Individuals use it for free. Workspaces, the paid tier, is for teams who want to share agents across their own Macs. There’s a Windows beta as well, which I think helps Apple’s case more than it hurts it. When the same app runs on both platforms, the Mac’s unified memory is the difference. Wrap up In talking with him, Terence mentioned he wouldn’t be surprised if a local model matches what today’s frontier models can do by this time next year. I believe him, and that’s the point. The frontier will keep moving, but good enough keeps moving too, and good enough is what most employees need most of the day. Apple spent the AI race building memory, bandwidth, and a framework instead of trying to match the frontier, and the narrative was that they were behind. Now the most capable open-weight model in the US is optimized for the Mac. Apple @ Work is exclusively brought to you by Mosyle, the only Apple Unified Platform. Mosyle is the only solution that integrates in a single professional grade platform all the solutions necessary to seamlessly and automatically deploy, manage, and protect Apple devices at work. Over 45,000 organizations trust Mosyle to make millions of Apple devices work ready with no effort and at an affordable cost. Request your EXTENDED TRIAL today and understand why Mosyle is everything you need to work with Apple. FTC: We use income earning auto affiliate links. More.