Can I Run Qwen 3.6 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated April 22, 2026
Yes, but it is tight
Yes, but it is tight — Qwen 3.6 35B-A3B at Q6_K needs about 29.7 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.3 GB before the runtime starts swapping. Expect ~32.8 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~32.8 tok/s
Get a personalized upgrade path →
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 | 120 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) |
Qwen 3.6 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 71 GB | ✗ No | — | — | 70 GB |
| Q8_0 | 38.2 GB | ✗ No | — | — | 37.2 GB |
| Q6_K | 29.7 GB | ✓ Yes | 64K | ~32.8 tok/s | 28.7 GB |
| Q5_K_M | 25.8 GB | ✓ Yes | 256K | ~37.3 tok/s | 24.8 GB |
| Q4_K_M | 22.1 GB | ✓ Yes | 256K | ~42.9 tok/s | 21.1 GB |
| Q3_K_M | 15.9 GB | ✓ Yes | 256K | ~57.5 tok/s | 14.9 GB |
| Q2_K | 12.5 GB | ✓ Yes | 256K | ~70.7 tok/s | 11.5 GB |
Which Qwen 3.6 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen 3.6 35B-A3B | 22.1 GB | ✓ Fits | ~42.9 tok/s |
| Qwen 3.6 27B | 19.3 GB | ✓ Fits | ~5 tok/s |
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 120 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
Can I run Qwen 3.6 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, but it is tight — Qwen 3.6 35B-A3B at Q6_K needs about 29.7 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving only ~2.3 GB before the runtime starts swapping. Expect ~32.8 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Qwen 3.6 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q6_K — it needs about 29.7 GB of the 32 GB available, downloads as roughly 28.7 GB, and runs at an estimated 32.8 tokens/sec with up to 64K of context.
What limits Qwen 3.6 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)
- Qwen 3.7 on Beelink SER9 (Ryzen AI 9, 32 GB)
- Qwen3.8 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)
Qwen 3.6 on GPUs
- Qwen 3.6 on NVIDIA GeForce RTX 5090
- Qwen 3.6 on NVIDIA GeForce RTX 5080
- Qwen 3.6 on NVIDIA GeForce RTX 5070 Ti
- Qwen 3.6 on NVIDIA GeForce RTX 5070