Can I Run Poolside Laguna XS 2.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

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 Q4_K_M needs about 22.6 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.4 GB before the runtime starts swapping. Expect ~170.6 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~170.6 tok/s

RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models24 GB
Memory bandwidth1008 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

Poolside Laguna XS 2.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

QuantMemory neededFits 24 GB?Max contextEst. speedDownload
F1668.6 GB✗ No66 GB
Q8_037.7 GB✗ No35.1 GB
Q6_K29.7 GB✗ No27.1 GB
Q5_K_M26 GB✗ No23.4 GB
Q4_K_M22.6 GB✓ Yes8K~170.6 tok/s19.9 GB
Q3_K_M16.7 GB✓ Yes32K~193.9 tok/s14.1 GB
Q2_K13.5 GB✓ Yes32K~209.6 tok/s10.8 GB

What to watch out for

RTX 4090 desktop limitations

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

FAQ

Can I run Poolside Laguna XS 2.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Yes, but it is tight — Laguna XS 2.1 33B-A3B at Q4_K_M needs about 22.6 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~1.4 GB before the runtime starts swapping. Expect ~170.6 tok/s (estimated), with room for about 8,192 tokens of context.

Which quantization of Poolside Laguna XS 2.1 should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Q4_K_M — it needs about 22.6 GB of the 24 GB available, downloads as roughly 19.9 GB, and runs at an estimated 170.6 tokens/sec with up to 8K of context.

What limits Poolside Laguna XS 2.1 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

Other Computers

Other Models on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)

Poolside Laguna XS 2.1 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Poolside Laguna XS 2.1 model page | Check your hardware