Can I run this LLM?
Can a Mac Studio M5 Ultra (512GB) run Llama 4 Scout (MoE)?
Llama · See model card · estimated for a 512.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Llama 4 Scout (MoE) at FP16 · 215.6 GB · 21–31 tok/s on a Mac Studio M5 Ultra (512GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 39.6 GB | 70–105 tok/s | Runs great |
| Q3_K_M | 51.8 GB | 60–90 tok/s | Runs great |
| Q4_K_M | 65.4 GB | 52–78 tok/s | Runs great |
| Q5_K_M | 76.6 GB | 47–70 tok/s | Runs great |
| Q6_K | 88.4 GB | 42–63 tok/s | Runs great |
| Q8_0 | 114.5 GB | 35–52 tok/s | Runs great |
| FP16 | 215.6 GB | 21–31 tok/s | Runs great |
Open the full calculator →Everything a Mac Studio M5 Ultra (512GB) runsLlama 4 Scout (MoE) on other machinesWhat to buy to run it →
Ran Llama 4 Scout (MoE) on a Mac Studio M5 Ultra (512GB)? Add your real numbers →