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

Written by Jakub Rusinowski · Last updated July 8, 2026

Yes — comfortably

Yes, comfortably — Qwen3-Coder 8B 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 ~20.2 tok/s (estimated), with room for about 65,536 tokens of context.

Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~20.2 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)

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

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F1617.9 GB✓ Yes64K~11.3 tok/s16 GB
Q8_010.4 GB✓ Yes64K~20.2 tok/s8.5 GB
Q6_K8.5 GB✓ Yes64K~25.4 tok/s6.6 GB
Q5_K_M7.6 GB✓ Yes64K~28.8 tok/s5.7 GB
Q4_K_M6.8 GB✓ Yes64K~32.9 tok/s4.8 GB
Q3_K_M5.4 GB✓ Yes64K~43.5 tok/s3.4 GB
Q2_K4.6 GB✓ Yes64K~52.9 tok/s2.6 GB

Which Qwen3-Coder sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
Qwen3-Coder 480B-A35B (MoE)291.6 GB✗ Too large
Qwen3-Coder 80B-A3B (MoE)51.6 GB✗ Too large
Qwen3-Coder 8B6.8 GB✓ Fits~32.9 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 Qwen3-Coder on Beelink SER9 (Ryzen AI 9, 32 GB)?

Yes, comfortably — Qwen3-Coder 8B 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 ~20.2 tok/s (estimated), with room for about 65,536 tokens of context.

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

Q8_0 — it needs about 10.4 GB of the 32 GB available, downloads as roughly 8.5 GB, and runs at an estimated 20.2 tokens/sec with up to 64K of context.

What limits Qwen3-Coder 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)

Qwen3-Coder on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | Qwen3-Coder model page | Check your hardware