How this works (as of Oct 15, 2026): we compare each model’s Ollama download size with your usable memory, keeping a few GB spare as our local AI guide recommends. On Apple Silicon that’s your unified memory; on a PC with a graphics card it’s the card’s VRAM (anything bigger runs on the processor and RAM, much more slowly). This is a rule of thumb, not a guarantee, and we haven’t benchmarked these models: we’ve only run Qwen 3.5 0.8B on a CPU-only Linux server. App notes come from LM Studio’s and Ollama’s official pages.

Sources

Prices and plans change often. Always confirm on the official site before you buy.