Can I Run EXAONE 3.5 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Written by Jakub Rusinowski · Last updated February 10, 2026

Yes, but it is tight

Yes, but it is tight — EXAONE 3.5 32B at Q6_K needs about 29.2 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.8 GB before the runtime starts swapping. Expect ~6.9 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~6.9 tok/s

Beelink SER9 (Ryzen AI 9, 32 GB) — what it gives a model

Usable memory for models32 GB
Memory bandwidth256 GB/s
Form factorMini PC
Operating systemWindows or Linux
Memory upgradeableYes
Price$859 (lib/data/ai-stations.ts (street price), checked 2026-07-06)

EXAONE 3.5 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1666.9 GB✗ No64 GB
Q8_036.9 GB✗ No34 GB
Q6_K29.2 GB✓ Yes16K~6.9 tok/s26.2 GB
Q5_K_M25.6 GB✓ Yes16K~7.9 tok/s22.7 GB
Q4_K_M22.3 GB✓ Yes32K~9.2 tok/s19.3 GB
Q3_K_M16.6 GB✓ Yes32K~12.7 tok/s13.6 GB
Q2_K13.5 GB✓ Yes32K~16 tok/s10.5 GB

Which EXAONE 3.5 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
EXAONE 3.5 32B22.3 GB✓ Fits~9.2 tok/s
EXAONE 3.5 7.8B6.6 GB✓ Fits~33.8 tok/s
EXAONE 3.5 2.4B2.9 GB✓ Fits~87.5 tok/s

Beelink SER9 32 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 EXAONE 3.5 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Yes, but it is tight — EXAONE 3.5 32B at Q6_K needs about 29.2 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.8 GB before the runtime starts swapping. Expect ~6.9 tok/s (estimated), with room for about 16,384 tokens of context.

Which quantization of EXAONE 3.5 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?

Q6_K — it needs about 29.2 GB of the 32 GB available, downloads as roughly 26.2 GB, and runs at an estimated 6.9 tokens/sec with up to 16K of context.

What limits EXAONE 3.5 on Beelink SER9 (Ryzen AI 9, 32 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 Beelink SER9 (Ryzen AI 9, 32 GB)

EXAONE 3.5 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | EXAONE 3.5 model page | Check your hardware