v0.30.10
Ollama release - check for model support, multi-GPU, and compatibility.
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 - Jun 18, 2026Six months ago, the idea of spending $1000/month per employee on AI was laughable Then the coding agents got good and now Uber has to cap their spending at $1500/month per employee per tool! I think the market is there for 10x on revenue - many companies haven't figured coding agents out yet
Agent or tool-use pattern - relevant to local AI workflow automation.
Summoning the Demon
Geohot take - high-signal on open-source AI, tinygrad, and builder philosophy.
GLM-5.2 is probably the most powerful text-only open weights LLM
Simon Willison signal - surfaces practical patterns before they spread.
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.