Can I run this LLM?
Can a Mac Studio M3 Ultra (96GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna XS 2.1 (MoE) at Q8_0 · 35.6 GB · 78–117 tok/s on a Mac Studio M3 Ultra (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.2 GB | 111–166 tok/s | Runs great |
| Q3_K_M | 15.6 GB | 105–157 tok/s | Runs great |
| Q4_K_M | 20.6 GB | 96–145 tok/s | Runs great |
| Q5_K_M | 24.0 GB | 91–137 tok/s | Runs great |
| Q6_K | 29.0 GB | 85–128 tok/s | Runs great |
| Q8_0 | 35.6 GB | 78–117 tok/s | Runs great |
| FP16 | 66.9 GB | 56–84 tok/s | Won't fit |
Open the full calculator →Everything a Mac Studio M3 Ultra (96GB) runsLaguna XS 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna XS 2.1 (MoE) on a Mac Studio M3 Ultra (96GB)? Add your real numbers →