CanIHost
Guide

How to Choose a GPU for Local AI: A Buyer's Framework

A decision framework for buying a GPU for local LLMs — VRAM first, bandwidth second, vendor stack third, with specific card recommendations by budget.

Updated August 28, 2025 · 7 min read

GPU buying advice for gaming rarely translates to local AI. Frames-per-second logic leads you to the wrong card, because inference optimizes for two different things: VRAM capacity (what models can run at all) and memory bandwidth (how fast they run). Here is a framework that puts those in the right order.

Priority 1: VRAM capacity

Capacity is the gate. A model either fits or it doesn't — and if it doesn't, no amount of speed saves the experience. At 4-bit quantization, budget roughly 0.6 GB per billion parameters plus ~1 GB of overhead:

  • 8 GB → 7B–8B comfortably, 12B–14B squeezed
  • 12 GB → 14B at Q4/Q5 comfortably
  • 16 GB → 14B at Q6/Q8, 32B at Q3
  • 24 GB → 32B at Q4/Q5, 70B at Q2 (with compromises)

Decide which model class you actually want to run in a year, not just today — VRAM is the one spec you cannot upgrade later. Most satisfied local-AI users wish they had bought more capacity, not more speed.

Priority 2: memory bandwidth

Speed tracks bandwidth almost linearly (see tokens per second). Within a capacity tier, the card with more bandwidth produces tokens faster. Notable bandwidth landmarks: ~270 GB/s (mid cards like the 4060), ~500 GB/s (4070 class), ~1 TB/s (4090 class).

Practical implication: a 12 GB card with 360 GB/s (used RTX 3060) and a 12 GB card with 504 GB/s (4070) host the same models — the second one just does it roughly 40% faster.

Priority 3: ecosystem (CUDA vs ROCm vs Vulkan)

Covered fully in CUDA vs ROCm: NVIDIA is the zero-friction default; AMD offers more VRAM per euro with a modest tax in setup effort; Vulkan keeps everything portable. If you value "it just works," weigh that into the price.

Cards by budget tier

TierCardVRAMBest for
Budget (used)RTX 3060 12 GB12The classic value entry; 13B Q4
Budget AMDRX 7800 XT1614B class on Linux/Vulkan
Mid newRTX 406087B–8B with speed
Mid usedRTX 30902424 GB at used prices — the value king
Upper midRTX 407012Balanced: capacity + real bandwidth
EnthusiastRTX 409024Fastest consumer inference
Value 24 GBRX 7900 XTX2424 GB cheaper, ROCm ecosystem
Apple pathM-series (32–64 GB unified)32–64Big models, quiet, no discrete GPU

The two cards that punch above their price for AI specifically: the used RTX 3060 12 GB (cheapest real capacity) and the used RTX 3090 (24 GB at half the price of new). The cards that don't make sense for AI: the RTX 4060 Ti 8 GB (same VRAM as 4060, more money) and any card under 6 GB.

Two honest warnings

  • Don't buy for "AI tops." Marketing tensor-core numbers matter little for single-stream local inference; bandwidth and capacity dominate. A "gaming" card at the right VRAM/bandwidth beats an "AI-branded" one with less.
  • Mind your platform. A 24 GB card wants a real PSU (750–850 W+) and case cooling; a Mac path avoids all of it but costs more per GB. Total-system thinking beats card-thinking.

The 10-second version

Pick the model class you want in two years, buy the cheapest card (new or used) whose VRAM hosts that class at 4-bit with headroom, prefer more bandwidth within that tier, and let the ecosystem preference break ties. Then verify: run your configuration through the checker before spending — it grades the entire model catalogue against the exact card you're considering, so you know what your money buys.