Can I Run Qwen3.8 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Written by Jakub Rusinowski · Last updated September 6, 2026

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)

Qwen3.8 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	58.1 GB	✗ No	—	—	55.6 GB
Q8_0	32.1 GB	✗ No	—	—	29.5 GB
Q6_K	25.3 GB	✓ Yes	32K	~8 tok/s	22.8 GB
Q5_K_M	22.2 GB	✓ Yes	32K	~9.1 tok/s	19.7 GB
Q4_K_M	19.3 GB	✓ Yes	64K	~10.6 tok/s	16.8 GB
Q3_K_M	14.4 GB	✓ Yes	64K	~14.6 tok/s	11.8 GB
Q2_K	11.7 GB	✓ Yes	64K	~18.4 tok/s	9.1 GB

Which Qwen3.8 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Qwen3.8-Max	1457.5 GB	✗ Too large	—
Qwen3.8 27B	19.3 GB	✓ Fits	~10.6 tok/s

What to watch out for

• 1 larger variant of Qwen3.8 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

Can I run Qwen3.8 on Beelink SER9 (Ryzen AI 9, 32 GB)?

Yes — Qwen3.8 27B at Q6_K needs about 25.3 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~6.7 GB spare), at ~8 tok/s (estimated), with room for about 32,768 tokens of context.

Which quantization of Qwen3.8 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?

Q6_K — it needs about 25.3 GB of the 32 GB available, downloads as roughly 22.8 GB, and runs at an estimated 8 tokens/sec with up to 32K of context.

What limits Qwen3.8 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

• Qwen3.8 on Mac mini M4 16 GB
• Qwen3.8 on Mac mini M4 Pro 64 GB
• Qwen3.8 on Framework Desktop 128 GB

Other Models on Beelink SER9 (Ryzen AI 9, 32 GB)

• Qwen3-Coder on Beelink SER9 (Ryzen AI 9, 32 GB)
• SmolLM2 on Beelink SER9 (Ryzen AI 9, 32 GB)
• SmolLM3 on Beelink SER9 (Ryzen AI 9, 32 GB)
• StarCoder 2 on Beelink SER9 (Ryzen AI 9, 32 GB)
• Aya 3B (Tiny Aya) on Beelink SER9 (Ryzen AI 9, 32 GB)

Qwen3.8 on GPUs

• Qwen3.8 on NVIDIA GeForce RTX 5090
• Qwen3.8 on NVIDIA GeForce RTX 5080
• Qwen3.8 on NVIDIA GeForce RTX 5070 Ti
• Qwen3.8 on NVIDIA GeForce RTX 5070

What This Model Is Good At

• Best local LLMs for coding
• Best local LLMs for general assistant
• Best local LLMs for rag

Model & Tools

• Qwen3.8 model page
• VRAM calculator
• Check your own hardware

← Can I Run It? | Qwen3.8 model page | Check your hardware