Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, but it is tight
Yes, but it is tight — Laguna XS 2.1 33B-A3B at Q6_K needs about 29.7 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~2.3 GB before the runtime starts swapping. Expect ~210 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~210 tok/s
| Usable memory for models | 32 GB |
| Memory bandwidth | 1792 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 68.6 GB | ✗ No | — | — | 66 GB |
| Q8_0 | 37.7 GB | ✗ No | — | — | 35.1 GB |
| Q6_K | 29.7 GB | ✓ Yes | 16K | ~210 tok/s | 27.1 GB |
| Q5_K_M | 26 GB | ✓ Yes | 32K | ~221.5 tok/s | 23.4 GB |
| Q4_K_M | 22.6 GB | ✓ Yes | 32K | ~233.6 tok/s | 19.9 GB |
| Q3_K_M | 16.7 GB | ✓ Yes | 64K | ~257.5 tok/s | 14.1 GB |
| Q2_K | 13.5 GB | ✓ Yes | 64K | ~272.7 tok/s | 10.8 GB |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — Laguna XS 2.1 33B-A3B at Q6_K needs about 29.7 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving only ~2.3 GB before the runtime starts swapping. Expect ~210 tok/s (estimated), with room for about 16,384 tokens of context.
Q6_K — it needs about 29.7 GB of the 32 GB available, downloads as roughly 27.1 GB, and runs at an estimated 210 tokens/sec with up to 16K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
← Can I Run It? | Poolside Laguna XS 2.1 model page | Check your hardware