Can I Run StarCoder 2 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated February 28, 2024
Yes — comfortably
Yes, comfortably — StarCoder 2 15B at Q8_0 needs about 17.9 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~14.1 GB spare and running at ~5.3 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~5.3 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) |
StarCoder 2 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 32.5 GB | ✗ No | — | — | 31 GB |
| Q8_0 | 17.9 GB | ✓ Yes | 16K | ~5.3 tok/s | 16.5 GB |
| Q6_K | 14.2 GB | ✓ Yes | 16K | ~6.8 tok/s | 12.7 GB |
| Q5_K_M | 12.5 GB | ✓ Yes | 16K | ~7.8 tok/s | 11 GB |
| Q4_K_M | 10.8 GB | ✓ Yes | 16K | ~9.1 tok/s | 9.4 GB |
| Q3_K_M | 8.1 GB | ✓ Yes | 16K | ~12.6 tok/s | 6.6 GB |
| Q2_K | 6.6 GB | ✓ Yes | 16K | ~16 tok/s | 5.1 GB |
Which StarCoder 2 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| StarCoder 2 15B | 10.8 GB | ✓ Fits | ~9.1 tok/s |
| StarCoder 2 7B | 5.7 GB | ✓ Fits | ~18.7 tok/s |
| StarCoder 2 3B | 2.9 GB | ✓ Fits | ~42.1 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 StarCoder 2 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, comfortably — StarCoder 2 15B at Q8_0 needs about 17.9 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~14.1 GB spare and running at ~5.3 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of StarCoder 2 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q8_0 — it needs about 17.9 GB of the 32 GB available, downloads as roughly 16.5 GB, and runs at an estimated 5.3 tokens/sec with up to 16K of context.
What limits StarCoder 2 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)
- Aya 3B (Tiny Aya) on Beelink SER9 (Ryzen AI 9, 32 GB)
- VibeThinker on Beelink SER9 (Ryzen AI 9, 32 GB)
- Yi 1.5 Family on Beelink SER9 (Ryzen AI 9, 32 GB)
- Aya Expanse on Beelink SER9 (Ryzen AI 9, 32 GB)
- BitNet b1.58 on Beelink SER9 (Ryzen AI 9, 32 GB)
StarCoder 2 on GPUs
- StarCoder 2 on NVIDIA GeForce RTX 5080
- StarCoder 2 on NVIDIA GeForce RTX 5070 Ti
- StarCoder 2 on NVIDIA GeForce RTX 5070
- StarCoder 2 on NVIDIA GeForce RTX 5060 Ti 16GB
What This Model Is Good At
Model & Tools
← Can I Run It? | StarCoder 2 model page | Check your hardware