Cheapest Mac to run Mixtral 8x22B
141B parameters (39B active) · quality index 17 · coding 15 · every Apple Silicon Mac ever sold, compared. It is a mixture-of-experts model: all 141B parameters must sit in memory, but only 39B compute per token, which is why it is faster than dense models of similar size.
The cheapest Mac that runs Mixtral 8x22B comfortably is a used Mac Studio M4 Max 16c/40c 128GB (2025) at about $2,511 EST. on the used market — running Q4_K_M quantization at roughly 12 tok/s with up to 64K tokens of context.
Every Mac that runs it, by used price
| Machine | Used price | Runs at | Est. speed | Max context |
|---|---|---|---|---|
| Mac Studio M4 Max 16c/40c 128GB (2025) | $2,511 EST. | Q4_K_M | 12 tok/s | 64K tokens |
| Mac Studio M1 Ultra 20c/48c 128GB (2022) | $2,951 EST. | Q4_K_M | 17 tok/s | 64K tokens |
| Mac Studio M2 Ultra 24c/60c 128GB (2023) | $2,999 EST. | Q4_K_M | 17 tok/s | 64K tokens |
| MacBook Pro M3 Max 16c/40c 128GB (2023) | $3,062 EST. | Q4_K_M | 8.5 tok/s | 64K tokens |
| Mac Studio M1 Ultra 20c/64c 128GB (2022) | $3,197 EST. | Q4_K_M | 17 tok/s | 64K tokens |
| Mac Studio M2 Ultra 24c/76c 128GB (2023) | $3,249 EST. | Q4_K_M | 17 tok/s | 64K tokens |
| Mac Studio M2 Ultra 24c/60c 192GB (2023) | $3,499 EST. | Q6_K | 13 tok/s | 64K tokens |
| Mac Studio M2 Ultra 24c/76c 192GB (2023) | $3,749 EST. | Q6_K | 13 tok/s | 64K tokens |
| MacBook Pro M4 Max 16c/40c 128GB (2024) | $3,772 EST. | Q4_K_M | 12 tok/s | 64K tokens |
| MacBook Pro M5 Max 18c/32c 128GB (2026) | $4,199 EST. | Q4_K_M | 13 tok/s | 64K tokens |
See all 12 machines, other price bases, and live currency conversion →
Run it
ollama run mixtral:8x22b pulls the default (≈Q4) build once you have Ollama installed.
Or skip the hardware
Cloud APIs serve Mixtral 8x22B at about $1.2 per million output tokens. The main site's break-even solver computes the daily usage where owning a Mac becomes cheaper than renting.
Open the interactive guide — speed simulator, TCO, all 75 machines →