AMD's NEW Zen 4 in 2026? Reviewing and Benchmarking the 7700x3D
Level1Techs - deep-dive hardware and Linux content for builder types.
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 - Jul 16, 2026SQLite should have (Rust-style) editions
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
Hugging Face blog post - check for new model releases, library updates, or ecosystem shifts.
Noctua NH-U14S DX4677 Quick Look With the Intel Xeon 600 Series
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
NVIDIA Announces Expanded Jetson Thor Lineup with Mid-Range T3000 and T2000 Modules
ServeTheHome coverage - server hardware reviews and benchmarks from a trusted source.
AMD ROCm 7.14 adds Gorgon Halo support before Ryzen AI Max PRO 400 systems launch
Non-CUDA GPU backend item - cross-vendor awareness, not RTX 3090 CUDA serving.
Grok Build is open source
Open-source licensing or release - affects what can run on owned hardware.
Newer Models, Same Advantage
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.