Local AI Advisor — Which LLM Can My PC Run?
Auto-detects your GPU, VRAM and RAM, then shows exactly which local LLMs you can run — with realistic tokens/sec, the right quantization, memory footprint, and the backend to use (Ollama, LM Studio, llama.cpp, vLLM, MLX). 61 GPUs, 47 models and a free-form estimator, all grounded in real memory-bandwidth & quant math. Free, private, in-browser.
Input
0 requiredResults
Results will appear here
About
Auto-detects your GPU, VRAM and RAM, then shows exactly which local LLMs you can run — with realistic tokens/sec, the right quantization, memory footprint, and the backend to use (Ollama, LM Studio, llama.cpp, vLLM, MLX). 61 GPUs, 47 models and a free-form estimator, all grounded in real memory-bandwidth & quant math. Free, private, in-browser.
Related Tools
Frequently Asked Questions
How does it work?
Advanced algorithms process your data instantly, right in your browser.
Is my data safe?
Yes! Everything stays on your device. We never store or transmit your data.
Can I use commercially?
Absolutely. Free for all personal and commercial projects.
How accurate is it?
Industry-standard precision with professional-grade algorithms.