Local AI + Homelab
LLM VRAM Calculator & Local AI GPU Planner
Estimate VRAM, RAM, context limits, and token speed before you choose hardware for local LLMs.
Calculate a local AI buildStart with a tool
Plan before you buy or build.
GPU + Value Analysis
GPU Upgrade Value Calculator
Compare price, resale value, VRAM, power draw, and PSU guidance to make an upgrade decision with the full cost in view.
Compare GPU upgrade valueExplore by goal
Build the system you want to run.
Popular practical guides
Start with proven reading.
GPU
RX 6700 XT to RTX 4070 Ti: an upgrade comparison
Performance, value, and practical reasons to make the switch.
Local AI + Homelab
Access private LLMs with Tailscale and Ollama
Run Ollama remotely without exposing it to the public internet.
Latest
Latest guides and experiments
Stop Guessing Your Next GPU: I Built a GPU Upgrade Value Calculator
PublishedI added a GPU Upgrade Value Calculator to help compare GPU upgrade costs, resale value, VRAM, power draw, PSU guidance, and practical capability tradeoffs. 
Local LLM VRAM Calculator & GPU Planner for Apple Silicon, NVIDIA, and Coding Agents
Published❘ UpdatedI added a Local AI VRAM Calculator & GPU Planner (Beta) to help compare GPUs, estimate model VRAM usage, and check local model fit. 
How to Access Ollama Remotely with Tailscale (2026 Guide)
Published❘ UpdatedConnect to Ollama securely from a laptop with Tailscale and no port forwarding. Includes the preferred Windows OLLAMA_HOST setup, Open WebUI, and Serve troubleshooting.
About the site
Built from practical work, not generic advice.
I am a software engineer based in Southern California. I share hands-on experiments, benchmarks, and lessons from building software, running local AI, and maintaining home infrastructure.
More about the site and its author