Samprix

What AI can your computer run?

Pick your graphics card or Mac and see which local models fit in its memory, before you download gigabytes you can’t use.

Free, no sign-up 27 GPUs & Macs · 39 models
Specs last checked: how

34 of 42 model downloads fit in the 16 GB VRAM of the RTX 5060 Ti 16 GB

at 4,096 tokens of context
  • Mistral Small 24B
  • Mistral Small 22B
  • Qwen3 14B
  • Phi-4 14B
  • Qwen2.5 14B

Next step up: Qwen3 32B needs 20 GB.

Full results for RTX 5060 Ti 16 GB

Local AI tools

Run models on your own machine

What AI Can My Computer Run?

Pick your graphics card or Mac and see which local AI models fit in its memory.

LLM VRAM Calculator

Pick a local model and context length and see how much GPU memory it needs, and which cards and Macs fit it.

Ollama & LM Studio Beginner’s Guide

Set up local AI on Windows or Mac, step by step.

Local AI Electricity Cost Calculator

What running a model on your own hardware costs, compared with the API.

Every graphics card and Mac we check

How much VRAM does a model need?

More tools

Text, AI plans and costs, and developer checks
AI Text Cleaner Paste text from ChatGPT, Claude or Gemini and get clean plain text back. Word, Character & Token Counter Count words, characters and tokens, and see how much of each chatbot’s limit you use. Context Window Checker Paste text or drop a PDF and see which ChatGPT, Claude, Gemini and local models can take all of it. AI Subscription Comparison ChatGPT, Claude and Gemini paid plans side by side: price, limits and features. AI Image Prompt Builder Build a detailed image prompt from subject, style, lighting and camera. Which AI Should I Use? Answer four questions and see which ChatGPT, Claude or Gemini plan fits, with reasons. AI API Cost Calculator Estimate monthly API cost across models, including caching and batch discounts. AI API Pricing by Model Every model’s API prices, and any two models compared head to head. AI Subscription vs API Calculator See how many messages a day it takes before a ChatGPT, Claude or Gemini plan beats paying per token.

From the makers’ own pages

Memory comes from NVIDIA’s and Apple’s spec pages, file sizes from the download page, each linked.

No made-up speeds

Nobody publishes tokens per second, so we don’t show them. Our estimates are labeled.

Dated and re-checked

New cards and models arrive often, so every figure shows when we last checked it.

© 2026 Samprix. Not affiliated with OpenAI, Anthropic or Google.

PrivacyTerms