Can I Run Nex-N2 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Written by Jakub Rusinowski · Last updated September 8, 2026

Yes, but it is tight

Yes, but it is tight — Nex-N2 mini at Q6_K needs about 31.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~0.6 GB before the runtime starts swapping. Expect ~50.1 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: low · Recommended quantization: Q6_K · Estimated speed: ~50.1 tok/s

Buy This HardwareApple Mac mini M4 (16GB) — 32 GB VRAM · 22 W board power Deploy in the Cloud NowNVIDIA A40 on RunPod — from $0.44/hr · rate checked 2026-08

or compare on Vast.ai

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)

Nex-N2 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	72.7 GB	✗ No	—	—	70 GB
Q8_0	39.9 GB	✗ No	—	—	37.2 GB
Q6_K	31.4 GB	✓ Yes	8K	~50.1 tok/s	28.7 GB
Q5_K_M	27.5 GB	✓ Yes	16K	~54.9 tok/s	24.8 GB
Q4_K_M	23.8 GB	✓ Yes	32K	~60.3 tok/s	21.1 GB
Q3_K_M	17.6 GB	✓ Yes	64K	~72.5 tok/s	14.9 GB
Q2_K	14.2 GB	✓ Yes	64K	~81.5 tok/s	11.5 GB

Which Nex-N2 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Nex-N2 Pro	244.7 GB	✗ Too large	—
Nex-N2 mini	23.8 GB	✓ Fits	~60.3 tok/s

What to watch out for

Only ~0.6 GB of headroom at Q6_K: a longer context or a second application can push this into swapping.
1 larger variant of Nex-N2 does not fit and would need CPU offload or different hardware.
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