A Value 128GB Local AI Node? The GMKtec EVO-X3
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
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 09, 2026Show HN: Let your AI agents paint big arrows, boxes and text on your screen
Agent or tool-use pattern - relevant to local AI workflow automation.
Impactful scheduling for GPU clusters
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
The model that didn't exist, so you made it yourself
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
GMKtec EVO-X3 Mini-PC Review
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
Tiny Corp charges $4,000 for four Radeon RX 9070 XT GPUs in new Tinybox AI workstation
Alphacool introduces single-slot water blocks for NVIDIA RTX PRO Blackwell and AMD Radeon AI PRO GPUs
Kioxia LD4 E1.L QLC NVMe SSD Announced
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.