<feed xmlns="http://www.w3.org/2005/Atom"> <id>https://technotim.com/</id><title>Techno Tim</title><subtitle>Techno Tim Home - Documentation and More</subtitle> <updated>2026-05-23T23:08:46-05:00</updated> <author> <name>Techno Tim</name> <uri>https://technotim.com/</uri> </author><link rel="self" type="application/atom+xml" href="https://technotim.com/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="https://technotim.com/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 Techno Tim </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Running the Latest vLLM on the NVIDIA DGX Spark</title><link href="https://technotim.com/posts/vllm-gb10-docker/" rel="alternate" type="text/html" title="Running the Latest vLLM on the NVIDIA DGX Spark" /><published>2026-05-21T08:00:00-05:00</published> <updated>2026-05-23T23:07:38-05:00</updated> <id>https://technotim.com/posts/vllm-gb10-docker/</id> <content type="text/html" src="https://technotim.com/posts/vllm-gb10-docker/" /> <author> <name>Techno Tim</name> </author> <category term="homelab" /> <category term="ai" /> <summary>When I built my local AI cluster on a pair of ASUS Ascent GX10s, the hard part was not serving a model. The hard part was getting a working vLLM image with current components. NVIDIA’s official image was already over a month behind by the time I needed it, and waiting on their release schedule was not an option. If you saw that post, you know the GX10 is an ARM64 machine built around NVIDIA’s ...</summary> </entry> <entry><title>I Built a 256GB Local AI Cluster on My Desk</title><link href="https://technotim.com/posts/local-ai-gx10/" rel="alternate" type="text/html" title="I Built a 256GB Local AI Cluster on My Desk" /><published>2026-05-18T08:00:00-05:00</published> <updated>2026-05-23T23:07:32-05:00</updated> <id>https://technotim.com/posts/local-ai-gx10/</id> <content type="text/html" src="https://technotim.com/posts/local-ai-gx10/" /> <author> <name>Techno Tim</name> </author> <category term="ai" /> <category term="homelab" /> <summary>I have been covering local and self-hosted AI for a few years now - from running models privately at home to what is still running in my homelab today. But to run the larger, more capable models, you need something more specialized than a general-purpose home server. I wanted to know how good local AI has actually gotten, so I built a mini AI cluster on my desk and used it for a real coding wo...</summary> </entry> <entry><title>GPU-Accelerated Remote Desktop on Linux from macOS - the Hard Way</title><link href="https://technotim.com/posts/gpu-accelerated-rdp/" rel="alternate" type="text/html" title="GPU-Accelerated Remote Desktop on Linux from macOS - the Hard Way" /><published>2026-04-13T08:00:00-05:00</published> <updated>2026-04-13T17:52:47-05:00</updated> <id>https://technotim.com/posts/gpu-accelerated-rdp/</id> <content type="text/html" src="https://technotim.com/posts/gpu-accelerated-rdp/" /> <author> <name>Techno Tim</name> </author> <category term="homelab" /> <summary>What started as “just set up RDP” turned into an all day rabbit hole about how Linux remote desktop actually works, why most of it doesn’t work with NVIDIA on ARM64, and what it actually takes to get GPU-accelerated H264 encoding over RDP from an Ubuntu machine to a Mac. What I was trying to do I have two ASUS Ascent GX10 machines running Ubuntu 24.04. They are ARM64 systems built around th...</summary> </entry> <entry><title>I Built a Real 3-2-1 Backup System with TrueNAS, Offsite Replication, and UNAS</title><link href="https://technotim.com/posts/321-backup/" rel="alternate" type="text/html" title="I Built a Real 3-2-1 Backup System with TrueNAS, Offsite Replication, and UNAS" /><published>2026-04-12T08:00:00-05:00</published> <updated>2026-04-12T08:00:00-05:00</updated> <id>https://technotim.com/posts/321-backup/</id> <content type="text/html" src="https://technotim.com/posts/321-backup/" /> <author> <name>Techno Tim</name> </author> <category term="truenas" /> <category term="homelab" /> <summary>What started as, “I just need a backup,” turned into a full rebuild. I wanted a real 3-2-1 backup system for my homelab without signing up for a giant cloud bill to cover roughly 30TB of data. That ended up meaning an offsite TrueNAS box, a redesign of the main NAS, and eventually a third copy on a different platform so pulling back one file would not turn into a ZFS project. Watch the vide...</summary> </entry> <entry><title>What I'm Running in My Homelab in 2026</title><link href="https://technotim.com/posts/homelab-services-tour-2026/" rel="alternate" type="text/html" title="What I&amp;apos;m Running in My Homelab in 2026" /><published>2026-03-15T08:00:00-05:00</published> <updated>2026-04-13T09:14:13-05:00</updated> <id>https://technotim.com/posts/homelab-services-tour-2026/</id> <content type="text/html" src="https://technotim.com/posts/homelab-services-tour-2026/" /> <author> <name>Techno Tim</name> </author> <category term="homelab" /> <summary>In my last homelab tour, I focused on the hardware. This time, I wanted to answer the question a lot of people asked after that video: what am I actually running on all of this infrastructure? So this is the software side of the lab in 2026. The services, the applications, and the systems that make the hardware useful. Some of this is practical. Some of it is for learning. Some of it replace...</summary> </entry> </feed>
