Can I run this LLM?
Can a NVIDIA RTX 4090 (24GB) run Laguna XS 2.1 (MoE)?
Laguna · openmdw-1.1 · estimated for a 24.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Laguna XS 2.1 (MoE) at Q3_K_M · 15.6 GB · 182–273 tok/s on a NVIDIA RTX 4090 (24GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 12.2 GB | 196–295 tok/s | Runs great |
| Q3_K_M | 15.6 GB | 182–273 tok/s | Runs great |
| Q4_K_M | 20.6 GB | 164–246 tok/s | Won't fit |
| Q5_K_M | 24.0 GB | 153–230 tok/s | Won't fit |
| Q6_K | 29.0 GB | 140–211 tok/s | Won't fit |
| Q8_0 | 35.6 GB | 126–190 tok/s | Won't fit |
| FP16 | 66.9 GB | 86–128 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 4090 (24GB) runsLaguna XS 2.1 (MoE) on other machinesWhat to buy to run it →
Ran Laguna XS 2.1 (MoE) on a NVIDIA RTX 4090 (24GB)? Add your real numbers →