This solo builder runs 24/7 local AI on his own hardware | Alex Finn

AI builder Alex Finn runs a 24/7 local AI setup using three Mac Studio 512 GB machines, a DGX Spark, and a custom RTX 5090 build, coordinated through a self-built fleet dashboard. He allocates tasks across machines and models like OpenClaw and Hermes to enable unlimited local inference without cloud subscriptions.

Alex Finn is an AI builder, YouTuber, and the creator of Vibe Code Academy, a community for people learning to build with AI tools. He runs one of the most ambitious local AI setups I’ve come across: three Mac Studio 512 GB machines, a DGX Spark, and a custom RTX 5090 build, all coordinated through a fleet dashboard he built himself. He’s spent five months figuring out which local models belong on which machines, how to wire them to Claude Code loops, and how to get a software factory running without babysitting it. Listen or watch on YouTube, Spotify, or Apple Podcasts What you’ll learn: How Alex chose between a Mac Studio 512 GB unified memory , DGX Spark, and RTX 5090, and what each is actually good for Why Tailscale is worth installing even on a single machine, and how it lets one agent manage your entire hardware fleet How the build loop and review loop in Claude Code work How to allocate tasks by machine and model Why unlimited local inference changes the use-case math in a way a $20 cloud subscription never can What OpenClaw and Hermes are each best suited for, and why Alex runs five agents total with failover baked in Brought to you by: Runway —The creative AI platform for images, video, and more Jira Product Discovery —Prioritize with insights, build with confidence In this episode, we cover: 00:00 https://www.youtube.com/watch?v=dAQsmhAiews Intro 02:58 https://www.youtube.com/watch?v=dAQsmhAiews&t=178s Alex’s hardware stack 03:48 https://www.youtube.com/watch?v=dAQsmhAiews&t=228s What “ambient AI” means 04:15 https://www.youtube.com/watch?v=dAQsmhAiews&t=255s Alex’s red-pill moment with OpenClaw 07:04 https://www.youtube.com/watch?v=dAQsmhAiews&t=424s Mac Studio vs. DGX Spark vs. RTX 5090 13:24 https://www.youtube.com/watch?v=dAQsmhAiews&t=804s How to set up local models with no technical knowledge Tailscale + OpenClaw/Hermes 17:16 https://www.youtube.com/watch?v=dAQsmhAiews&t=1036s Fleet control dashboard: assigning 24/7 tasks across machines 20:42 https://www.youtube.com/watch?v=dAQsmhAiews&t=1242s Local models as security scanners feeding Claude Code 22:25 https://www.youtube.com/watch?v=dAQsmhAiews&t=1345s How Alex allocates GLM 5.2, Qwen 3.6, and Ornith 1.0 by task 24:28 https://www.youtube.com/watch?v=dAQsmhAiews&t=1468s OpenClaw vs. Hermes: the honest comparison 26:55 https://www.youtube.com/watch?v=dAQsmhAiews&t=1615s The software factory: build loop, review loop, rocket emoji 31:55 https://www.youtube.com/watch?v=dAQsmhAiews&t=1915s Lightning round: favorite hardware, favorite model, prompting style 34:46 https://www.youtube.com/watch?v=dAQsmhAiews&t=2086s Where to find Alex Tools referenced: • Claude Code: https://claude.ai/code https://claude.ai/code • OpenClaw: https://openclaw.ai/ https://openclaw.ai/ • Hermes: https://hermes-agent.nousresearch.com/ https://hermes-agent.nousresearch.com/ • Tailscale: https://tailscale.com/ https://tailscale.com/ • Codex OpenAI : https://openai.com/codex https://openai.com/codex • GLM 5.2 z.ai : https://huggingface.co/zai-org/GLM-5.2 https://huggingface.co/zai-org/GLM-5.2 • Qwen 3.6 Alibaba : https://huggingface.co/Qwen/Qwen3.6-35B-A3B https://huggingface.co/Qwen/Qwen3.6-35B-A3B • Ornith 1.0: https://github.com/deepreinforce-ai/Ornith-1 https://github.com/deepreinforce-ai/Ornith-1 • Gemma 4: https://huggingface.co/collections/google/gemma-4 https://huggingface.co/collections/google/gemma-4 • Playwright browser testing : https://playwright.dev/ https://playwright.dev/ • Vercel preview deploys : https://vercel.com/ https://vercel.com/ Other references: • DGX Spark Nvidia : https://www.nvidia.com/en-us/products/workstations/dgx-spark/ https://www.nvidia.com/en-us/products/workstations/dgx-spark/ • Mac Studio Apple : https://www.apple.com/mac-studio/ https://www.apple.com/mac-studio/ • How to design AI agent loops: schedules, goals, and subagents in Claude Code and Codex: https://www.lennysnewsletter.com/p/how-to-design-ai-agent-loops-schedules https://www.lennysnewsletter.com/p/how-to-design-ai-agent-loops-schedules Where to find Alex Finn: LinkedIn: https://www.linkedin.com/in/alex-finn-1848684a https://www.linkedin.com/in/alex-finn-1848684a/ YouTube: https://www.youtube.com/@AlexFinnOfficial https://www.youtube.com/@AlexFinnOfficial Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ https://www.chatprd.ai/ Website: https://clairevo.com/ https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ https://www.linkedin.com/in/clairevo/ Production and marketing by https://penname.co/ https://penname.co/ . For inquiries about sponsoring the podcast, email email protected /cdn-cgi/l/email-protection .