I built a page that tells you what AI model your laptop can run
5 hours ago
- The text describes analyzing hardware configuration to determine the most capable local model with good performance.
- It compares model tiers: Entry (1B parameters), Mid (7B), Large (70B), and SOTA (1T+), with corresponding RAM needs.
- Estimates assume quantized models (4-bit) for consumer hardware; actual performance depends on quantization quality, model architecture, and optimization tools.
- SOTA models like GPT-4o, Claude 3.5, and Gemini Ultra are estimated at 1T+ parameters.