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

Written by Jakub Rusinowski · Last updated September 6, 2026

Yes — comfortably

Yes, comfortably — VibeThinker 3B at Q8_0 needs about 4.9 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~27.1 GB spare and running at ~46.4 tok/s (estimated), with room for about 131,072 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~46.4 tok/s

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 W board power Deploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

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

Usable memory for models	32 GB
Memory bandwidth	256 GB/s
Form factor	Mini PC
Operating system	Windows or Linux
Memory upgradeable	Yes
Price	$859 (lib/data/ai-stations.ts (street price), checked 2026-07-06)

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

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	7.8 GB	✓ Yes	128K	~27.3 tok/s	6.2 GB
Q8_0	4.9 GB	✓ Yes	128K	~46.4 tok/s	3.3 GB
Q6_K	4.2 GB	✓ Yes	128K	~56.7 tok/s	2.5 GB
Q5_K_M	3.8 GB	✓ Yes	128K	~63.1 tok/s	2.2 GB
Q4_K_M	3.5 GB	✓ Yes	128K	~70.7 tok/s	1.9 GB
Q3_K_M	3 GB	✓ Yes	128K	~88.6 tok/s	1.3 GB
Q2_K	2.7 GB	✓ Yes	128K	~102.9 tok/s	1 GB

Which VibeThinker sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
VibeThinker 3B	3.5 GB	✓ Fits	~70.7 tok/s
VibeThinker 1.5B	2.4 GB	✓ Fits	~113.2 tok/s

What to watch out for

This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.

Beelink SER9 32 GB limitations

Shares system memory with the iGPU, so the usable model budget is well below the nominal 32 GB.
Memory bandwidth, not capacity, is the limit here — expect single-digit tokens/sec on large models.

Recommended setup

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

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
32 GB unified memory at 256 GB/s, shared between CPU and GPU.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is inferred from the parameter count because this model does not publish its full attention configuration.

FAQ