So as part of my ongoing testing of the M5 Ultra Mac Studio<\/a>, as well as experimenting on other Mac and Windows systems, I\u2019ve installed some local LLMs and I\u2019m beginning to tinker. Here\u2019s how things are going.<\/p>\n 1\/4Hermes Agent can be used with cloud or local models.<\/p>\n I started by installing the open-source Hermes Agent<\/a> on the Mac Studio. Hermes is a self-hosted AI agent desktop app that works on macOS, Windows, and Linux. It\u2019s completely free to use if you stick to local LLMs. Since this M5 Ultra Mac Studio has 256GB of unified memory, I could run just about any model I want. This is how things quickly get overwhelming. There are more models out there than I can count<\/a>, and some have specialized uses. Generally, models with many billions of parameters are able to do more than smaller ones with only a few billion. And since we don\u2019t have to worry about paying for tokens when running a model locally, I figured I\u2019d go big to start.<\/p>\n Using Hermes\u2019 straightforward onboarding interface and model picker, I chose the Qwen 3.8 Flash Next<\/a> model \u2014 a 125-billion parameter model that\u2019s around 105GB in size. I also plan on spending some time with much smaller Qwen models on devices like an M6 Mac Mini, M5 MacBook Air, an Asus TUF Gaming A14 with AMD Strix Halo processor, and, eventually, RTX Spark. (Care to share what local models and hardware you use? You know where to leave your comments. \ud83e\udee1)<\/p>\n It wasn\u2019t long to get up and running with Hermes and Qwen, and even make them controllable via my phone by using a Telegram bot<\/a>. But then, I was presented with my usual nemesis when it comes to using AI: the text box.<\/p>\n \u201cWhat do I do with this thing?\u201d<\/p>\n My Hermes daily briefing, sent to me daily via Telegram. Basic, I know.<\/p>\n First up, to get things going, I followed some helpful YouTube advice<\/a> and had Hermes make me a daily morning briefing \u2014 to just start small with a cron job and ensure things are working. It scans my email and calendar, tells me anything worth my immediate attention, and gives me a short weather report. It\u2019s not all that useful, and you obviously don\u2019t need a $12,000 computer to build it, but it\u2019s something I can develop over time. The brief kept failing to generate at first, but then I eventually figured out that macOS couldn\u2019t be asleep when the job fired up at 7:30am. Duh! It works like clockwork now, but I have to think of more info for it to pull for me to make the results more helpful.<\/p>\n A more useful task was reorganizing my Steam library. I have over 400 games on Steam, and I recently started categorizing them for when I want to play something new on a whim. Steam doesn\u2019t categorize your games for you, so you instead have to do it manually, one-by-one. But here\u2019s where an agentic lackey could fit right in. I asked, \u201cCan you reorganize my Steam library?\u201d Hermes could see most of my games by just viewing the already installed Steam client. It quickly came up with some organization options for me. I decided to have it organize my games by genre, but leave some of my own specialized categories(favorites, co-op titles, party games, games to play with my wife, etc.).<\/p>\n You have to give a local AI some permissions over your machine for it to take actions for you, and in the case of my game library I had to register a Steam web API key<\/a> and give it to Hermes. Once it had that access, it only took a few minutes for it to churn through sorting all the games into categories. And the API key was easy to revoke right after, since I don\u2019t need it further. The idea is for it to just do this heavy lifting for me once, and then I\u2019ll file new games into the categories as I eventually buy them. It did a fine job overall, and now my Steam library is easily browsable.<\/p>\n 1\/2Starting the process of having Hermes organize my Steam library.<\/p>\n Another simple thing I did was data analysis. I had Hermes take a look at financial records to crunch some numbers for me, and I also had it make me a spec comparison spreadsheet for a new laptop. These are small things, but they\u2019re both tasks I cannot or will not trust with any cloud service \u2014 I don\u2019t want to upload that sensitive data to the cloud, and in the case of a new laptop, that info was under embargo. Keeping them on my computer was the difference in me using this tool or not.<\/p>\n The bigger bit of automation I\u2019m currently working on is a script to run a series of laptop benchmark tests. I run all our benchmarks manually, and tending to a laptop to run a dozen or so tests \u2014 three times over, to take the average \u2014 is incredibly time-consuming. I\u2019d love to automate at least some of it. Even walking Hermes through all of the required procedures and getting it to spit out vibe coded Python scripts has been a bit of an endeavor, and it remains a work in progress. But I\u2019m hoping to make some positive headway.<\/p>\n Apple demoed this cluster of four Mac Studios wired up in a cluster for local AI at a briefing I attended last month. That\u2019s nearly $50,000 worth of compute.<\/p>\n It\u2019s still early days of me working with Hermes, and I\u2019m hoping this is just the tip of the iceberg on the useful things I get it to do for me. But it\u2019s also clear that even these powerful local models don\u2019t make for a magical assistant that can do anything. Things still don\u2019t always work as intended \u2014 my daily briefing already broke, multiple times.<\/p>\n I view Hermes and local AI as just a tool, a computer program to run on my computer. I don\u2019t want a digital friend. I\u2019m not saying \u201cthank you\u201d or \u201cplease,\u201d or typing \u201csorry\u201d when I change my mind on something. I\u2019m remaining as stone-cold and indifferent when ordering it around as I am clicking a mouse around an operating system.<\/p>\n I hope to remain vigilant and cautious while I continue testing and learning with local AI. Let\u2019s see where it takes me.<\/p>\n Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.Antonio G. Di BenedettoAIClose<\/p>\n AI<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n See All AI<\/a><\/p>\n AppleClose<\/p>\n Apple<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n See All Apple<\/a><\/p>\n macOSClose<\/p>\n macOS<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n See All macOS<\/a><\/p>\n MicrosoftClose<\/p>\n Microsoft<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n See All Microsoft<\/a><\/p>\n ReportClose<\/p>\n Report<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n See All Report<\/a><\/p>\n TechClose<\/p>\n Tech<\/p>\n Posts from this topic will be added to your daily email digest and your homepage feed.<\/p>\n FollowFollow<\/p>\n![\"My](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/hermes-telegram-daily-briefing-cron-job.jpg\"\/)
<\/a><\/p>\n![\"<em>Starting](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/Screenshot-2026-10-09-at-5.35.23-PM.png\"\/)
<\/a>![\"<em>The](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/Screenshot-2026-10-11-at-12.53.12-AM.png\"\/)
<\/a>PreviousNext<\/p>\n![\"Apple](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/10\/100926_Apple_Mac_Studio_M5_Ultra_local_AI_cluster_ADiBenedetto_0002.jpg\"\/)
<\/a><\/p>\n