CanIRun.ai: The Free Browser Tool That Tells You If Your Machine Can Actually Run That LLM
There’s a new free tool called CanIRun AI that checks your hardware and tells you which models will actually run well before you download anything.
So instead of guessing and hitting out-of-memory errors…it grades every model against your machine.
What it does (right in your browser, no install):
→ detects your setup (RAM / CPU / GPU / VRAM)
→ scores each model for fit, speed, and context length
→ grades every quantization level (Q4_K_M, Q6_K, Q8_0, etc.)
→ labels what runs great vs okay vs too heavy
It covers most of the open-weight stack, Llama, Qwen, Gemma, Mistral, DeepSeek, Phi and more, pulling requirements from llama.cpp, Ollama, and LM Studio.
Link: canirun.ai Screenshot 2026-08-24 at 6.17.11 PM
100% opensource
CanIRun.ai solves a real pain point for local AI users: guessing whether a model will fit your hardware before you download it.
It's a free, open-source, browser-based tool — no install required — that reads your CPU, GPU, RAM, and VRAM directly in-browser (nothing is sent to a server) and checks that profile against a database of 55+ open-weight models, including Llama, Qwen, Gemma, Mistral, and DeepSeek families.
For each model, it shows a runability grade — Runs great, Runs well, Decent, Tight fit, Barely runs, or Too heavy — broken down by quantization level (Q4_K_M, Q6_K, Q8_0, etc.), pulling its requirement data from llama.cpp, Ollama, and LM Studio.
Caveat: these are browser-API estimates, not real benchmarks — actual performance can vary based on your inference framework, drivers, and background load. Worth using as a first-pass filter, not a final verdict.