Can I run this LLM?
Can a Mac Studio M2 Ultra (192GB) run Gemma 4 31B?
Gemma · Apache 2.0 · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 31B at Q8_0 · 32.6 GB · 13–19 tok/s on a Mac Studio M2 Ultra (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 13.2 GB | 23–35 tok/s | Runs great |
| Q4_K_M | 18.6 GB | 19–28 tok/s | Runs great |
| Q5_K_M | 21.9 GB | 17–25 tok/s | Runs great |
| Q6_K | 25.3 GB | 15–23 tok/s | Runs great |
| Q8_0 | 32.6 GB | 13–19 tok/s | Runs great |
| FP16 | 61.4 GB | 8–11 tok/s | Tight / slow |
Open the full calculator →Everything a Mac Studio M2 Ultra (192GB) runsGemma 4 31B on other machinesWhat to buy to run it →
Ran Gemma 4 31B on a Mac Studio M2 Ultra (192GB)? Add your real numbers →