On this pageStart with the job and budgetUnderstand the memory that mattersRead benchmark evidence properlyTreat price as a dated, local observationUse this before payingSources
DT

Written and reviewed by DeviceterraPractical guidance · Updated November 11, 2026

THE SHORT ANSWER

Choose hardware by the largest model and task you actually need, then compare total system cost, memory headroom, software support, power, and measured results. Do not shop by AI TOPS alone.

THE FULL GUIDE

Here is what matters, why it matters and how to check it on your own setup.

01

Start with the job and budget

Write down the task first: short writing, coding, PDF search, image understanding, or several people using one machine. Then decide how much waiting is acceptable and what you can spend on the complete system, not only the GPU.

For a first personal assistant, a computer you already own with 16 GB RAM can be a sensible trial. If you want a GPU, the used RTX 3060 12 GB is a common budget candidate, but local prices and card condition vary. For large models, compare systems with 64–128 GB unified memory and high memory bandwidth.

02

Understand the memory that matters

Dedicated VRAM is memory on a graphics card. Unified memory is one pool shared by the CPU and GPU, as on Apple Silicon and AMD Ryzen AI Max systems. Neither pool is fully available to the model: the operating system, app, context, and other programs use part of it.

A model download size is not a safe memory budget. Runtime buffers and conversation context need additional room. When a model exceeds VRAM, it may still run by moving work to system RAM, often with a large speed penalty.

A cautious starting point; confirm exact model file and context before buying
Hardware memoryPractical first experimentsPurchase meaning
8 GB system RAM, CPU onlyVery small 1B–3B quantized text modelsTry an existing computer first; upgrade RAM or whole system only if a measured need appears
16 GB system RAM, CPU or Apple base modelSmall models; selected 4B–8B quantized models with careful contextGood entry point for learning and one-user tasks, not a guarantee of speed
8 GB dedicated GPU VRAMSmall to mid-size models, typically around 7B–9B at low quantizationCheck GPU support and leave room for context and desktop display
12 GB dedicated GPU VRAMMany 7B–14B quantized experiments, exact fit depends on model/contextStrong value can come from used cards; inspect condition and power requirements
24–32 GB dedicated GPU VRAMLarger dense models or faster smaller ones, depending on quantizationHigh performance, but total PC, PSU, cooling, and card cost are substantial
64–128 GB unified memoryLarger models can load locally, generally with speed trade-offsFor users who need model capacity and prefer compact systems over discrete GPU builds
03

Read benchmark evidence properly

Tokens per second measures how quickly generated text appears; it is not answer quality. A useful comparison names the exact model, quantization, engine, context, prompt/output length, hardware configuration, and whether the result is measured, community-submitted, or estimated.

For example, a public 2026 RTX 3060 test reports Qwen2.5 14B Q4_K_M around 26–29 tokens per second under its stated setup. That result is evidence that one configuration worked; it does not predict every RTX 3060, model version, or long-context workload. A 2026 16 GB Mac mini community benchmark project reports task accuracy as well as resource use, which is more useful for classification than a speed-only score.

04

Treat price as a dated, local observation

Manufacturer launch prices describe a region and a date. Retail prices change, stock can disappear, and import costs, shipping, taxes, warranty, and local voltage or repair access affect what you really pay.

In a November 2026 US sold-listing snapshot, the RTX 3060 12 GB showed a $340 median from 296 sales. Another tracker reported about $300 from only three qualified sales in September. The disagreement is a useful reminder: show sample size and collection date, and check your own market before buying. NVIDIA's RTX 5090 official starting price is $1,999; the DGX Spark founder MSRP was changed to $4,699 in February 2026. These figures are not local checkout quotes.

05

Use this before paying

  • Check the exact memory capacity and whether it is dedicated or unified.
  • Check model/runtime support for the operating system and GPU backend.
  • Price the entire system: GPU, case, motherboard, power supply, RAM, storage, shipping, and power backup where needed.
  • Use local sold listings when possible. For used GPUs, test under load and check temperature, fan noise, ports, warranty, and return terms.
  • Choose two models and one real task. Run a repeatable test before committing to a costly upgrade.
PLAIN ENGLISH

Words you may see in this guide

RAM
The working memory used by your computer and apps.
VRAM
The memory on a dedicated graphics card. Shared graphics may use system RAM.
Context
The text and other input the model can use for its current answer.
Quantization
A way to make model weights smaller. It can change memory use and answer quality.
Engine
The software that loads the model and runs it.
RAG
A workflow that finds useful document passages before asking a model to answer.
Benchmark
A repeatable test. A result is useful only when you know the setup and task.
RESEARCH SOURCES

Official facts and real user evidence

Official documentation supports product and model facts. Community discussions show real setups, failures, and questions. A community result is supporting evidence, not a promise that another computer will perform the same way.

YOUR NEXT STEP

Watch a real test. Check what fits your computer.

See practical local AI tests from DeviceTerra, then use MamiLens to build a hardware-aware shortlist for your own setup.

This guide is educational. Model software, licenses, and hardware support can change. Check official sources before an important deployment.