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 18, 2026Beelink ME Pro NAS launches with Ryzen AI 9 HX 370 and up to 132TB storage and 256GB DDR5 memory
Memory management signal - matters for fitting large models across 72GB total VRAM.
Thanks HN for 15 years of support and helping me find my life's work
Controlling Reasoning Effort in LLMs
Sebastian Raschka - deep technical writing on training, evaluation, and model internals.
Next Gen Server Memory On Display: DDR5-8000 RDIMMs and MRDIMM Gen2 Hits DDR5-12800
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
The AMD Instinct MI350P is a HBM PCIe AI Accelerator That Has Been All Over
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.