Can I Run Poolside Laguna XS 2.1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Written by Jakub Rusinowski · Last updated August 15, 2026

Yes — comfortably

Yes, comfortably — Laguna XS 2.1 33B-A3B at Q8_0 needs about 37.7 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~90.3 GB spare and running at ~42.3 tok/s (estimated), with room for about 262,144 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~42.3 tok/s

Framework Desktop (Ryzen AI Max+ 395, 128 GB) — what it gives a model

Usable memory for models128 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableNo — soldered

Poolside Laguna XS 2.1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB): memory by quantization

QuantMemory neededFits 128 GB?Max contextEst. speedDownload
F1668.6 GB✓ Yes256K~26.1 tok/s66 GB
Q8_037.7 GB✓ Yes256K~42.3 tok/s35.1 GB
Q6_K29.7 GB✓ Yes256K~50.3 tok/s27.1 GB
Q5_K_M26 GB✓ Yes256K~55.2 tok/s23.4 GB
Q4_K_M22.6 GB✓ Yes256K~60.7 tok/s19.9 GB
Q3_K_M16.7 GB✓ Yes256K~72.9 tok/s14.1 GB
Q2_K13.5 GB✓ Yes256K~82 tok/s10.8 GB

What to watch out for

Framework Desktop 128 GB 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 Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Yes, comfortably — Laguna XS 2.1 33B-A3B at Q8_0 needs about 37.7 GB of the 128 GB usable on Framework Desktop (Ryzen AI Max+ 395, 128 GB), leaving ~90.3 GB spare and running at ~42.3 tok/s (estimated), with room for about 262,144 tokens of context.

Which quantization of Poolside Laguna XS 2.1 should I use on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

Q8_0 — it needs about 37.7 GB of the 128 GB available, downloads as roughly 35.1 GB, and runs at an estimated 42.3 tokens/sec with up to 256K of context.

What limits Poolside Laguna XS 2.1 on Framework Desktop (Ryzen AI Max+ 395, 128 GB)?

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 Framework Desktop (Ryzen AI Max+ 395, 128 GB)

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