BEST of Everything CPU? The AMD EPYC 8005 Sorano
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 - Jun 30, 2026Featuring Every Eval Ever Results on Hugging Face Model Pages
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
Why Specialization Is Inevitable
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
AMD EPYC 8005 Sorano Completely Changes AMD SP6
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
AMD Pivots From HBM to LPDDR5X For New Versal Premium Gen 2 Memory on Package Chips
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
SteamOS 3.8.20 Beta improves VRAM handling and updates Mesa graphics driver
Memory management signal - matters for fitting large models across 72GB total VRAM.
DiScoFormer: One transformer for density and score, across distributions
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.