Testing Local AI With Hermes Agent and Qwen on an M5 Ultra Mac Studio
Learning to use local AI is exciting, overwhelming, and frustrating
- Who
- Antonio G. Di Benedetto
- What
- shares hands-on experience running local AI agents Hermes Agent with local Qwen models on Mac Studio
- Quote
So as part of my ongoing testing of the M5 Ultra Mac Studio , as well as experimenting on other Mac and Windows systems, I’ve installed some local LLMs and I’m beginning to tinker.
What happened
A Verge writer began running local LLMs on an M5 Ultra Mac Studio with 256GB of unified memory, installing the open-source Hermes Agent desktop app and the 125-billion-parameter Qwen 3.8 Flash Next model, about 105GB in size. Early tasks included a daily briefing via Telegram, reorganizing a 400-plus-game Steam library, and local data analysis; the writer is now working on automating laptop benchmark tests.
The story so far
The Verge writer Antonio G. Di Benedetto installed the open-source Hermes Agent desktop app and the 125-billion-parameter Qwen 3.8 Flash Next model, about 105GB in size, on an M5 Ultra Mac Studio with 256GB of unified memory, and is running local LLM tasks including a daily Telegram briefing, reorganizing a 400-plus-game Steam library, and local data analysis. He is now working on automating laptop benchmark tests. Di Benedetto said the setup is completely free to use if you stick to local LLMs, but a local AI needs permissions over the machine to take actions: for the game library he had to register a Steam web API key and give it to Hermes. The daily briefing kept failing to generate at first until he figured out that macOS could not be asleep when the job fired at 7:30am.
Keep reading
Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation PipelineTrending now
- 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
- 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
- 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
- 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-17