Can I Run GPT-OSS on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated August 15, 2026
Yes — comfortably
Yes, comfortably — GPT-OSS 20B at Q8_0 needs about 23.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~8.6 GB spare and running at ~21.3 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~21.3 tok/s
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
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) |
GPT-OSS on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 43 GB | ✗ No | — | — | 41.8 GB |
| Q8_0 | 23.4 GB | ✓ Yes | 128K | ~21.3 tok/s | 22.2 GB |
| Q6_K | 18.3 GB | ✓ Yes | 128K | ~26.8 tok/s | 17.1 GB |
| Q5_K_M | 16 GB | ✓ Yes | 128K | ~30.5 tok/s | 14.8 GB |
| Q4_K_M | 13.8 GB | ✓ Yes | 128K | ~34.9 tok/s | 12.6 GB |
| Q3_K_M | 10.1 GB | ✓ Yes | 128K | ~46.4 tok/s | 8.9 GB |
| Q2_K | 8.1 GB | ✓ Yes | 128K | ~56.7 tok/s | 6.9 GB |
Which GPT-OSS sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GPT-OSS 120B | 71.9 GB | ✗ Too large | — |
| GPT-OSS 20B | 13.8 GB | ✓ Fits | ~34.9 tok/s |
What to watch out for
- 1 larger variant of GPT-OSS does not fit and would need CPU offload or different hardware.
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 GPT-OSS on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, comfortably — GPT-OSS 20B at Q8_0 needs about 23.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~8.6 GB spare and running at ~21.3 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of GPT-OSS should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q8_0 — it needs about 23.4 GB of the 32 GB available, downloads as roughly 22.2 GB, and runs at an estimated 21.3 tokens/sec with up to 128K of context.
What limits GPT-OSS 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)
- Granite 3.0 on Beelink SER9 (Ryzen AI 9, 32 GB)
- IBM Granite 4.0 on Beelink SER9 (Ryzen AI 9, 32 GB)
- IBM Granite 4.1 on Beelink SER9 (Ryzen AI 9, 32 GB)
- IBM Granite 4.2 on Beelink SER9 (Ryzen AI 9, 32 GB)
- InternLM 3 on Beelink SER9 (Ryzen AI 9, 32 GB)
GPT-OSS on GPUs
- GPT-OSS on NVIDIA GeForce RTX 5080
- GPT-OSS on NVIDIA GeForce RTX 5070 Ti
- GPT-OSS on NVIDIA GeForce RTX 5070
- GPT-OSS on NVIDIA GeForce RTX 5060 Ti 16GB