User
Write something
My Home Lab
I design my home lab like a puzzle where all the pieces can be added or removed. When I use AI, I want to run local models when I can, and only use cloud models when it is needed. - Zo Computer, Prototyping. Runs cloud, and local models - MSI EdgeXpert - DGX Spark, AI Supercomputer, Local model serving - Mac Studio, M2 Max 32GB, Agent host, local embeddings - Mac Mini, M4 24GB, Agent host, local embeddings - MacBook Pro, M5 16GB, mobile, connectivity to the lab - HP Z2 G9, i9 64GB, 8GB VRAM, Workstation (dual boot) Windows/Ubuntu - Raspberry Pi, RPi 4 2GB, Always-on network node, VPN exit, subnet routing - Synology NAS - Tailscale, Mesh VPN - one private network across every machine AI Models - DeepSeek V4.1 Flash, Cloud - qwen3.6-35b-a3b, Spark - local model serving - nemotron-3.5-lightning:30b-a3b, Spark - local model serving - text-embedding-nomic-embed-text-v1.5, LM Studio, on the computer that runs Agent Zero Harnesses - Zo Computer, Cloud hosted, Prototyping - Hermes, A self-improving, open-source AI agent that runs persistently on your server or machine and remembers what it learns across sessions. - Agent Zero, A framework for building autonomous AI agents that can operate independently, learn, and execute tasks across various systems. I worked in IT Operations and never used AI specifically, so this year I bought hardware for AI, to add to my home lab. What am I working on? - AI memory including context in chat - Robotics and AI interface - Testing other AI harnesses like OpenHuman and Tiny Humans as long as I can host locally
0
0
Hardware update
So I was able to find 2 more RPi 5’s with the same specs. I also picked up a cluster rack so I will have 3 soon to setup my cluster and start building out my setup more deliberately.
2
0
Starting Point
Happy Saturday... I joined this community months ago and haven't really had time to dig in yet. I bought a RPi 5 with 8gb RAM and 256gb SSD and recently came across a decent deal for (3) USB 3.0 - 30 TB Ext SSDs under $70 to use as my NAS. Curious if anyone here has experience with a similar setup. I'm hoping that it will work for my intended use. I plugged one of them into my Parrot OS Laptop and it was recognized right away so that's encouraging. Also, just realizing the "Courses" section available to this community. Pretty stoked to see that I have so many resources at my fingertips here. Should help keep me on track.
Server RAM
I have an Intel S3420 server board that I am trying to add ram to and it will not post. Both are registered 1333 ddr3 ECC unless I am wrong. Any help is greatly appreciated, it on my Proxmox machine. Two different sticks in the pic below. Smaller is 4Gb and larger is 8Gb
Server RAM
Upgraded my Proxmox nics
I’ve upgraded the old Intel X520 NICs in my Lenovo P520 workstations to Intel XXV710 network adapters, which natively support 25 Gbps per port (in addition to 10 Gbps and 1 Gbps). The XXV710 is designed for much more efficiently and successfully allows the processor to enter deep C-states. Even though the card is faster, your Lenovo P520 will likely consume less power in idle mode. While I’m not upgrading to 25GbE just yet, this prepares my setup for future developments. The Intel XXV710 features superior hardware offloading and excellent SR-IOV support. The Proxmox advantage: you can split the physical 25G port into dozens of "Virtual Functions" (VFs) and pass them directly through to your VMs. This provides your VMs with near 100% hardware speed at extremely low CPU overhead. Furthermore, if you utilize SDN (Software-Defined Networking) within Proxmox and set up virtual network tunnels between nodes, these packets are processed by the XXV710's hardware rather than being handled by your P520's processor. In short: you get increased speed, lower latency, a lower idle power bill, and better integration with modern Proxmox features.
3
0
1-30 of 52
Home Lab Explorers
skool.com/homelabexplorers
Build, break, and master home labs and the technologies behind them! Dive into self-hosting, Docker, Kubernetes, DevOps, virtualization, and beyond.
Leaderboard (30-day)
Powered by