Can I run this LLM?
Can a MacBook Pro M5 Max (128GB) run Gemma 4 26B-A4B (MoE)?
Gemma · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Gemma 4 26B-A4B (MoE) at FP16 · 50.5 GB · 39–58 tok/s on a MacBook Pro M5 Max (128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 12.7 GB | 88–132 tok/s | Runs great |
| Q4_K_M | 17.0 GB | 77–115 tok/s | Runs great |
| Q5_K_M | 21.2 GB | 68–103 tok/s | Runs great |
| Q6_K | 23.2 GB | 65–97 tok/s | Runs great |
| Q8_0 | 26.9 GB | 59–89 tok/s | Runs great |
| FP16 | 50.5 GB | 39–58 tok/s | Runs great |
Open the full calculator →Everything a MacBook Pro M5 Max (128GB) runsGemma 4 26B-A4B (MoE) on other machinesWhat to buy to run it →
Ran Gemma 4 26B-A4B (MoE) on a MacBook Pro M5 Max (128GB)? Add your real numbers →