Can I run this LLM?
Can a MacBook Pro M2 Max (32GB) run Gemma 4 26B-A4B (MoE)?
Gemma · Apache 2.0 · estimated for a 32.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 26B-A4B (MoE) at Q4_K_M · 15.3 GB · 47–70 tok/s on a MacBook Pro M2 Max (32GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 10.9 GB | 53–80 tok/s | Runs great |
| Q4_K_M | 15.3 GB | 47–70 tok/s | Runs great |
| Q5_K_M | 18.0 GB | 44–65 tok/s | Tight / slow |
| Q6_K | 20.8 GB | 41–61 tok/s | Won't fit |
| Q8_0 | 26.8 GB | 36–53 tok/s | Won't fit |
| FP16 | 50.5 GB | 24–36 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M2 Max (32GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →
Ran Gemma 4 26B-A4B (MoE) on a MacBook Pro M2 Max (32GB)? Add your real numbers →