Can I Run Qwen 3 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Written by Jakub Rusinowski · Last updated April 28, 2025

Yes, but it is tight

Yes, but it is tight — Qwen 3 32B at Q6_K needs about 29.8 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.2 GB before the runtime starts swapping. Expect ~6.8 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~6.8 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)

Qwen 3 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1668.5 GB✗ No65.6 GB
Q8_037.8 GB✗ No34.8 GB
Q6_K29.8 GB✓ Yes16K~6.8 tok/s26.9 GB
Q5_K_M26.2 GB✓ Yes16K~7.8 tok/s23.2 GB
Q4_K_M22.8 GB✓ Yes32K~9 tok/s19.8 GB
Q3_K_M16.9 GB✓ Yes64K~12.4 tok/s14 GB
Q2_K13.7 GB✓ Yes64K~15.6 tok/s10.8 GB

Which Qwen 3 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Qwen 3 235B-A22B (MoE)144.3 GB✗ Too large
Qwen 3 32B22.8 GB✓ Fits~9 tok/s
Qwen 3 30B-A3B (MoE)20 GB✓ Fits~67.9 tok/s
Qwen 3 14B11.1 GB✓ Fits~19.1 tok/s
Qwen 3 8B7 GB✓ Fits~32.1 tok/s

What to watch out for

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 Qwen 3 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Yes, but it is tight — Qwen 3 32B at Q6_K needs about 29.8 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.2 GB before the runtime starts swapping. Expect ~6.8 tok/s (estimated), with room for about 16,384 tokens of context.

Which quantization of Qwen 3 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?

Q6_K — it needs about 29.8 GB of the 32 GB available, downloads as roughly 26.9 GB, and runs at an estimated 6.8 tokens/sec with up to 16K of context.

What limits Qwen 3 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)

Qwen 3 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Qwen 3 model page | Check your hardware