Can I run this LLM?
Can a MacBook Pro M3 Max (36GB) run Gemma 4 26B-A4B (MoE)?
Gemma · Apache 2.0 · estimated for a 36.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 26B-A4B (MoE) at Q5_K_M · 21.2 GB · 42–63 tok/s on a MacBook Pro M3 Max (36GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 12.7 GB | 58–87 tok/s | Runs great |
| Q4_K_M | 17.0 GB | 49–73 tok/s | Runs great |
| Q5_K_M | 21.2 GB | 42–63 tok/s | Runs great |
| Q6_K | 23.2 GB | 39–59 tok/s | Tight / slow |
| Q8_0 | 26.9 GB | 35–53 tok/s | Won't fit |
| FP16 | 50.5 GB | 21–32 tok/s | Won't fit |
Open the full calculator →Everything a MacBook Pro M3 Max (36GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →
Ran Gemma 4 26B-A4B (MoE) on a MacBook Pro M3 Max (36GB)? Add your real numbers →