LLMRequirements.com
Loading…

Pick the right hardware
to run local LLMs.

Tell us what you want to run — a use case, a memory target, or a specific open-weights model. We'll match it to real builds with current prices, community-measured tokens/sec, and idle & active power draw.

Start picking hardware
—builds compared
—open-source LLMs

Tell us what you want

Pick one of the three modes. You can switch at any time.

48GB Comfortable for 70 B Q4 dense
$2,000 Mid-range — 30 B comfortably, 70 B Q4 within reach

Pick one or more models you want to run. We'll size for the largest.

Quantization
Categories
Availability

After the picker

Once you have a shortlist, dig deeper.

Every build, side by side → Full comparison table — 65+ builds across Apple Silicon, NVIDIA, AMD, Intel. Open-weights models → 53 models rated by use case — SOTA cells flag best-in-class. Compare side-by-side → Pick 2-5 builds or models and compare tokens/sec, power, prices head-to-head. State of Local AI → Snapshot: dense-vs-MoE fork, per-bracket picks, what would flip the picture.