Intel Xeon 6980P Granite Rapids Performance On Linux Over The Past Year Hey folks, welcome back to Self-Hosted Tech. If you’ve been following the channel or the blog for a while, you know we love pushing enterprise hardware to its absolute limits in our home labs. Today, we’re taking a deep dive into an absolute monster of a processor: the Intel Xeon 6980P, part of the Granite Rapids family. Over the past year, we’ve watched the Linux kernel and the open-source ecosystem evolve to fully support this silicon. Granite Rapids isn’t just another CPU with more cores; it represents a massive architectural shift aimed squarely at the local AI and heavy virtualization markets. ...

Claude Code & AI: A Game Changer for Reverse-Engineering Hardware on Linux If you’ve spent any time in the self-hosting or homelab communities, you already know the feeling. You score a fantastic deal on a piece of enterprise hardware, a niche IoT sensor, or a cheap Wi-Fi card off eBay. You excitedly plug it into your Linux server, run lsusb or lspci, and… nothing. The kernel doesn’t recognize it. A quick Google search reveals that the manufacturer abandoned driver development in 2015, and the only existing drivers are closed-source blobs compiled for Windows XP. ...

HP Elitebook 6 G1Q Powered By Snapdragon X1 Plus Sees Linux Patches If you’ve been hanging around the homelab, self-hosting, and local AI communities lately, you’ve probably noticed a quiet but massive shift happening in the hardware world. For years, we’ve been stuck in an x86 duopoly. Intel and AMD have served us well, but when it comes to power efficiency—especially for always-on, low-power self-hosted nodes or portable local AI rigs—ARM architecture has been sitting on the sidelines looking very tempting. ...

Inside Hyperdrive: How We Solved A Rare Hyperdrive MySQL Caching Bug If you’ve been following the self-hosting scene for a while, you know that the dream is simple: run your own services, own your data, and keep latency low. Cloudflare’s Hyperdrive has been a game-changer for a lot of us in that regard. It pools database connections and caches query results at the edge, which means your self-hosted MySQL database sitting in a closet at home can suddenly feel like it’s running in a data center across the street. ...

Under The Hood, Off The Hot Path: How D1 Scales To Millions Of Databases Welcome back to Self-Hosted Tech! If you’ve been running a homelab for any amount of time, you already know that databases are the beating heart of almost every application we deploy. Whether you’re spinning up Nextcloud, tracking your smart home metrics in Home Assistant, or building a custom wrapper for your local LLMs, you need somewhere to store that data. ...

4-Hour Battery Storage Is Cheaper To Install Than Gas Turbines All Across Globe (and What It Means for Your Homelab) Welcome back to Self-Hosted Tech. If you’re reading this or watching the video, you already know that we talk a lot about the hardware that powers our digital lives—servers, network switches, local AI rigs, and the software that ties it all together. But there is one foundational element that we sometimes take for granted until it disappears: power. ...

Some Networking Fixes Being Diverted To Linux 7.4, AI/LLM Activity Still Increasing Hey everyone, welcome back to Self-Hosted Tech. If you’ve been following the homelab and self-hosting scene lately, you’ve probably noticed a massive shift in what we’re doing with our spare hardware. Gone are the days when a homelab was just a dusty old desktop running a few Docker containers for Pi-hole and Nextcloud. Today, our racks are buzzing with the hum of high-wattage GPUs, and our storage arrays are filling up with multi-gigabyte model weights. ...

Complete Homelab AI Stack Guide: Run Your Own Local AI Welcome back to Self-Hosted Tech! If you’ve been hanging around the homelab community for the last year, you’ve probably noticed that local AI has completely taken over the conversation. We went from running Pi-hole and Plex to suddenly hosting large language models (LLMs) in our closets. But let’s be honest: diving into local AI can feel overwhelming. Between Hugging Face repositories, quantization formats like GGUF, Python environments, and vector databases, it’s easy to get lost in the weeds. ...

Run Local AI with No GPU: Your CPU Is All You Need If you’ve been following the explosion of AI over the last couple of years, you might be under the impression that to run your own large language models (LLMs) locally, you need a massive, $2,000+ graphics card with 24GB of VRAM. Well, I’m here to let you in on a little secret: the GPU cartels want you to think that, but it’s simply not true. ...

Where We Expect AMD EPYC 9006 CPUs In The Era Of Agentic AI If you’ve been following the self-hosting and local AI scenes over the last couple of years, you know that the conversation has been completely dominated by GPUs. How much VRAM do you have? Can you fit a 70B parameter model in Llama 3? How many RTX 3090s can you safely plug into a single motherboard before your house’s circuit breaker gives up? ...