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 - Oct 12, 2026Doory - Open-Source Canva
Open-source licensing or release - affects what can run on owned hardware.
New Sakana AI paper: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS). Blog: pub.sakana.ai/mass/ Paper: arxiv.org/abs/2610.12176 How do we keep improving AI when tasks become too complex for humans to reliably evaluate? The model eventually hits a supervision bottleneck.
Agent or tool-use pattern - relevant to local AI workflow automation.
AMD EPYC 8005 SKU List and Value Analysis: Mainstream Sorano’s Big Stride
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Marvell Structera X 3406 and 3506 CXL 3.2 Memory Expanders
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
AMD Ryzen AI Halo with Ryzen AI Max+ PRO 495 launches at $7,299 with 192GB memory
Memory management signal - matters for fitting large models across 72GB total VRAM.
PELADN’s Ryzen AI Max+ PRO 495 workstation costs $7,470 with 192GB RAM, and the company suggests buying four
NVIDIA Rubin PCIe GPUs confirmed in HPE ProLiant Gen13 presentation
Bus or storage bandwidth topic - relevant to the H12SSL-i's PCIe 4.0 layout.
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.