Can I run this LLM?
Can a Mac Studio M3 Ultra (96GB) run Laguna S 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna S 2.1 (MoE) at Q3_K_M · 54.0 GB · 72–108 tok/s on a Mac Studio M3 Ultra (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 54.0 GB | 72–108 tok/s | Runs great |
| Q4_K_M | 73.1 GB | 61–92 tok/s | Won't fit |
| Q5_K_M | 87.9 GB | 55–83 tok/s | Won't fit |
| Q6_K | 97.9 GB | 52–78 tok/s | Won't fit |
| Q8_0 | 125.0 GB | 44–66 tok/s | Won't fit |
| FP16 | 235.2 GB | 28–41 tok/s | Won't fit |
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsLaguna S 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna S 2.1 (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →