Disclaimer

This page was written and translated automatically by AI and checked by software against its sources, with no human editing. Specifications come from the sources listed; memory requirements and speeds are estimates calculated with published formulas. How we use AI

All memory requirements and speeds on this site are estimates calculated from specifications and formulas, not our own measurements. Actual memory use and speed vary with the inference engine (for example llama.cpp, vLLM or MLX), the quantization file, context length, driver and operating system version, and other running software; speed can differ by a large factor. “Fits” describes llama.cpp’s default load check only, not peak memory while generating.

We make no warranty that this information is accurate, complete or current and accept no liability for any loss arising from its use. Check the manufacturer's specifications and your own tests before buying hardware.