100% free no uploads no sign-up

can my pc run ai?

Find out which local AI models your computer can handle — Llama, Qwen, Gemma, DeepSeek and more. No download, no sign-up.

What your browser can see

WebGPUchecking…
GPU vendor / architecturehidden by browser
RAM (browser-reported)not shared
CPU threads—
GPU max buffer—
16-bit GPU maths—

Browsers round memory and cap it at 8 GB, and they never reveal your GPU's video memory (VRAM). Enter your real numbers below for an accurate answer — on Windows: Task Manager → Performance; on Mac: Apple menu → About This Mac.

largest model size that should run comfortably (4-bit)enter your RAM
Model sizeNeeds (approx.)Your PCWhere it runs
1B~1.6 GB❌ unlikelyenter your RAM/VRAM to check
3B~2.8 GB❌ unlikelyenter your RAM/VRAM to check
8B~5.8 GB❌ unlikelyenter your RAM/VRAM to check
14B~9.4 GB❌ unlikelyenter your RAM/VRAM to check
32B~20.2 GB❌ unlikelyenter your RAM/VRAM to check
70B~43 GB❌ unlikelyenter your RAM/VRAM to check
Popular open models and what they need
ModelParametersQ4 memory (approx.)Your PC
Llama 3.2 1B1.2B~1.7 GB❌ unlikely
Llama 3.2 3B3.2B~2.9 GB❌ unlikely
Llama 3.1 8B8B~5.8 GB❌ unlikely
Llama 3.3 70B70B~43 GB❌ unlikely
Qwen3 4B4B~3.4 GB❌ unlikely
Qwen3 8B8.2B~5.9 GB❌ unlikely
Qwen3 14B14.8B~9.9 GB❌ unlikely
Qwen3 32B32.8B~20.7 GB❌ unlikely
Qwen3 30B-A3B
mixture-of-experts: needs memory for all 30B, but runs about as fast as a 3B model
30.5B~19.3 GB❌ unlikely
Gemma 3 1B1B~1.6 GB❌ unlikely
Gemma 3 4B4.3B~3.6 GB❌ unlikely
Gemma 3 12B12.2B~8.3 GB❌ unlikely
Gemma 3 27B27.4B~17.4 GB❌ unlikely
Mistral 7B7.3B~5.4 GB❌ unlikely
Mistral Small 24B24B~15.4 GB❌ unlikely
Phi-4-mini 3.8B3.8B~3.3 GB❌ unlikely
Phi-4 14B14.7B~9.8 GB❌ unlikely
DeepSeek-R1-Distill-Qwen 1.5B1.8B~2.1 GB❌ unlikely
DeepSeek-R1-Distill-Qwen 7B7.6B~5.6 GB❌ unlikely
DeepSeek-R1-Distill-Llama 8B8B~5.8 GB❌ unlikely
DeepSeek-R1-Distill-Qwen 14B14.8B~9.9 GB❌ unlikely
DeepSeek-R1-Distill-Qwen 32B32.8B~20.7 GB❌ unlikely
DeepSeek-R1-Distill-Llama 70B70.6B~43.4 GB❌ unlikely

How the estimate works

Most people run local models in 4-bit (Q4) quantised form — the default in tools like Ollama and LM Studio — because it cuts memory use by about 4× compared with full 16-bit weights while keeping most of the quality. A useful rule of thumb is 0.6 GB per billion parameters plus about 1 GB of overhead. Long chats, big documents and larger context windows add more on top, so treat the numbers as a minimum.

Model sizeApprox. memory at Q4Typical hardware
1B~1.6 GBAlmost any laptop or recent phone
3B~2.8 GB8 GB RAM laptop
7–8B~5.8 GB16 GB RAM, or an 8 GB graphics card
14B~9.4 GB12–16 GB graphics card, or a 16–24 GB Mac
32B~20.2 GB24 GB graphics card, or a 32 GB+ Mac
70B~43 GBTwo 24 GB GPUs, or a 64 GB+ Mac

GPU, CPU or Mac — what changes

Getting started

  1. Use the check above to pick a model size that fits comfortably.
  2. Install a free local runner such as Ollama or LM Studio.
  3. Download a 4-bit version of a model in that size — start small (3B–8B) and move up if it's fast enough.
  4. Close heavy apps (games, many browser tabs) to free memory before loading bigger models.

Local models are private and free to run, but the biggest cloud assistants are still more capable for many tasks. Compare their plans in our AI pricing guide, or count prompt sizes with the token counter.

Frequently asked questions

How much RAM do I need to run an AI model locally?

A rough rule for 4-bit (Q4) models is about 0.6 GB per billion parameters plus ~1 GB overhead: an 8B model needs ~5.8 GB, a 14B ~9.4 GB, a 70B ~43 GB. Longer conversations (bigger context) need extra.

Do I need a graphics card?

No, but it helps a lot. Models that fit in your GPU's video memory run many times faster. Without a GPU, small models (1B–8B) still run on the CPU — just slowly. Apple Silicon Macs share memory between CPU and GPU, so they run fairly large models well.

Why can't the website see my exact RAM or VRAM?

For privacy, browsers round your memory, cap it at 8 GB and don't reveal video memory at all. That's why you can type in your real numbers.

What is WebGPU?

A browser feature that lets web pages use your graphics card. If it's available, small AI models can run directly in a web page without installing anything.

Which app should I use to run models?

Popular free options include Ollama, LM Studio and llama.cpp. They download quantised (usually 4-bit) versions of open models and run them on your own computer.

Is anything sent to a server?

No. The check runs entirely in your browser.