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 08, 2026Docker Agent
Container tooling update - relevant to the Docker-based serving stack.
Kioxia LD4 E1.L QLC NVMe SSD Announced
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Microsoft Launches Surface Laptop Ultra, Surface RTX Spark Dev Box
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Xsight Labs E1L DPU for Lower-Power 200Gbps DPUs
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Microsoft announces $6,000 price for Surface RTX Spark Dev Box with 128GB memory, $2000 more than AMD’s Ryzen AI Halo
Memory management signal - matters for fitting large models across 72GB total VRAM.
Adobe Photoshop, Premiere and Illustrator now have AI-built open-source clones
Open-source licensing or release - affects what can run on owned hardware.
Introducing Falcon ASR
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
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.