Interactive hardware compass

Which AI PC fits your local LLM?

Four inputs produce a practical shortlist. The finder estimates model weights, context cache and runtime headroom, then matches that requirement to specific complete systems in our maintained catalog.

Your requirements

Find the right memory and systems

The calculator estimates fast-memory needs for quantized inference and shows specific compatible configurations; it is not a performance guarantee.

1 Which model size do you want to run locally?

7B–8Bfast entry point 12B–14Bmore quality 20B–32Bdemanding 65B–70Blarge model 100B+professional class

2 · Desired context lengthLong context substantially increases KV cache. 3 · Main workloadMore components require additional memory. 4 · Highest priorityThis determines the recommended hardware path. Approximate system budgetBudget does not change memory needs, only the realistic route.

Your memory class

16 GB of fast memory as a starting point

Estimated need7–9 GBModel + context + headroom

Recommended class16 GB VRAMdiscrete GPU

Suitable system typeMidrange GPU PCwith at least 32 GB system RAM

Why this recommendation?

Specific matches from the system catalogThe shortlist considers memory, hardware path, priority, and budget tier.

View matches

Specific complete systems

Models that fit your selection

Cataloged configurations are being compared with your result.

Loading the system catalog …

See every cataloged system and its differences

What the calculation includes

Conservative headroom

typical Q4 weight size for the model class
allowance for longer KV cache
runtime and selected workflow reserve
comparison with the memory capacities of specific systems

What no calculator knows for sure

Model and software still matter

architecture and exact quantization
Flash Attention and backend support
multimodal encoders and concurrent users
how much unified memory the system exposes

Next step

Understand the memory values behind your result

Our VRAM guide explains weights, KV cache, offloading and unified memory without unnecessary jargon.

Read the VRAM guide