Build Planning
Parts lists that fit the workload, from the entry tier up.
A local-AI build is chosen from the model backwards: pick the models you actually run, size VRAM for them, then pick the cheapest card that gets there. These builds follow that order, with the power, cooling and platform details that decide whether the system is quiet, stable and upgradeable.
RTX 5090 32GB Flagship Build (2026)
The 2026 single-card speed ceiling: an RTX 5090 32GB build against the 2026-09-28 price snapshot, with sourced-only board numbers.
- Sep 6, 2026 · 3 min readDual RTX 3090 70B Build (48GB, 2026)Two used 24GB cards give 48GB for 70B-class local inference. What it costs at the 2026-09-28 snapshot, and sourced tok/s.
- Sep 5, 2026 · 3 min readThe 48GB VRAM Local LLM BuildHow to get 48GB of VRAM for 70B-class local LLMs: dual RTX 3090 vs used A6000 48GB — power, cooling, PCIe and real community tok/s.
- Sep 4, 2026 · 2 min read$1,500 Sweet-Spot Build (Used RTX 3090)The best tokens-per-dollar in 2026: one used RTX 3090 24GB runs 32B models interactive and 70B at patient speeds. Prices as of 2026-09-28.
- Sep 4, 2026 · 2 min read$800 Entry Build for Local LLMsThe cheapest sensible local-LLM machine: a 12GB card that runs 7B–14B models well. Prices as of 2026-09-28.
- Sep 4, 2026 · 4 min readBudget Build Monthly — September 2026First monthly build review: three tiers vs. the 2026-09-04 price snapshot, plus value picks — Intel's 24GB at $599 and AMD's 32GB at $1,329.
- Sep 15, 2026 · 7 min readTwo RTX 3060s: 16 tok/s Dense, 94 tok/s MoEThe same dual-3060 rig runs a 30B dense model at 16 tok/s and a 30B mixture-of-experts at 94. That 6x spread decides whether the build is worth it.
- Sep 4, 2026 · 2 min readRun 70B Models on Two Used RTX 3090sThe 48GB route: running 70B-class models at usable speeds on a pair of used RTX 3090s for around $2,600. Pricing as of 2026-09-28.
- Sep 29, 2026 · 11 min readX local-model bench digest — Sep 29, 2026Local-LLM throughput measured on X: 37 posts, 111 runs — hardware, quantization, engine and tok/s with a source link for every number.
- Sep 14, 2026 · 8 min readX local-model bench digest — Sep 14, 2026Local-LLM throughput measured on X: 12 posts, 25 runs — hardware, quantization, engine and tok/s with a source link for every number.