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 24, 2026Our team just shipped Fugu-Ultra v1.1! 🐡 By dynamically orchestrating the latest frontier models, we pushed performance up by 7.9 points. We are now beating Fable 5 in complex coding and reasoning tasks without even having Fable 5 in our agent pool. Collective intelligence is the future.
Performance data that could inform model selection or serving config.
Why Software Factories Fail (or: harness engineering is not enough)
Show HN: Palmier Pro - Open-source macOS video editor built for AI
Open-source licensing or release - affects what can run on owned hardware.
Adding a backup Internet WAN on my OPNsense Router
Geerling content - practical hardware testing, often with Linux and ARM angles.
NVIDIA’s Jensen Huang joins X, uses first post to discuss AI
AMD confirms Zen 7 EPYC Florence and Instinct MI600 for 2028, Zen 8 Ravenna follows in 2030
Server platform hardware - directly relevant to the H12SSL-i / EPYC stack.
AMD Advancing AI 2026 Keynote Live Coverage
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
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.