This was never a good deal.
Geerling content - practical hardware testing, often with Linux and ARM angles.
Independent publication // local-first AI // field reports from owned systems
Nodehome
A running publication about local models, private inference, self-hosted agents, weird hardware, research sweeps, and the builders wiring their own AI stack together.
AI is getting physical again. It shows up in terminals, racks, side projects, and ugly little workflows people actually control.
Latest
Daily Sweep - Jul 30, 2026I Finally Got My DREAM Network Server
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Wendell and Robots at AMD's Advancing AI Event
Level1Techs - deep-dive hardware and Linux content for builder types.
Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
Agent or tool-use pattern - relevant to local AI workflow automation.
GPU Management: Why Idle GPUs Are the New Grounded Aircraft
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
Best Buy raises high-end GeForce RTX 50 pricing, first RTX 5080 now exceeds RTX 5090 MSRP
GPU hardware mention - directly relevant to the build or resale market.
Kioxia launches CM10 PCIe 6.0 enterprise SSDs with up to 61.44TB capacity
Bus or storage bandwidth topic - relevant to the H12SSL-i's PCIe 4.0 layout.
AI's top startups are barely publishing their research
RAG or embedding pipeline development - potential local workflow pattern.
Field Reports
builds, experiments, notesThree RTX 3090s, One 32B Model: A Pipeline-Parallel Canary
A current field note on why the 3x3090 serving path moved through pipeline parallelism, not tensor parallelism, for the tested 32B AWQ model.
Gemma 4 12B And The Sensory Agent Lane
A public-safe read on Gemma 4 12B as a local sensory preprocessor: useful for seeing, hearing, and structuring observations without turning into an action system.
Hardware
machines, thermals, economicsPower Caps On Three RTX 3090s: Bursts Versus Sustained Load
A measured note on 300W bursty inference, lower caps for sustained runs, and why power-cap sweet spots are workload-specific.
Parallel Agent Serving Is A Hardware Shape Now
A field-report read on 14x RTX 3090 agent serving, EXL3, FP8 KV cache, Aphrodite, and why concurrency is becoming the local hardware metric.