Can I Run Llama 3.1 Family on Beelink SER9 (Ryzen AI 9, 32 GB)?

Superseded model. Llama 3.1 Family has been superseded by Llama 4. This page is kept for reference; the newer family is a better starting point. View Llama 4 →

Written by Jakub Rusinowski · Last updated July 23, 2024

Yes — comfortably

Yes, comfortably — Llama 3.1 8B Instruct at Q8_0 needs about 10.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~21.6 GB spare and running at ~20.3 tok/s (estimated), with room for about 131,072 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~20.3 tok/s

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)

Llama 3.1 Family on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	17.9 GB	✓ Yes	64K	~11.3 tok/s	16 GB
Q8_0	10.4 GB	✓ Yes	128K	~20.3 tok/s	8.5 GB
Q6_K	8.4 GB	✓ Yes	128K	~25.5 tok/s	6.6 GB
Q5_K_M	7.5 GB	✓ Yes	128K	~28.9 tok/s	5.7 GB
Q4_K_M	6.7 GB	✓ Yes	128K	~33.1 tok/s	4.8 GB
Q3_K_M	5.3 GB	✓ Yes	128K	~43.9 tok/s	3.4 GB
Q2_K	4.5 GB	✓ Yes	128K	~53.4 tok/s	2.6 GB

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 computed from this model's published attention configuration.

FAQ