| Machine | Fits? | Tokens/sec | ||||
|---|---|---|---|---|---|---|
| Loading… | ||||||
Every model has its own page: see the full answer for this model →
Pick a model. See whether it fits and the estimated speed on every Mac and mini PC. Local LLM speed is mostly memory bandwidth ÷ model size, so we can estimate any machine, then check against real runs.
| Machine | Fits? | Tokens/sec | ||||
|---|---|---|---|---|---|---|
| Loading… | ||||||
Every model has its own page: see the full answer for this model →