Can I Run Codestral on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated May 29, 2024
Yes — comfortably
Yes, comfortably — Codestral 22B at Q5_K_M needs about 18.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~13.6 GB spare and running at ~5.3 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: high · Recommended quantization: Q5_K_M · 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) |
Codestral on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 47.1 GB | ✗ No | — | — | 44.4 GB |
| Q8_0 | 26.3 GB | ✓ Yes | 32K | ~3.6 tok/s | 23.6 GB |
| Q6_K | 20.9 GB | ✓ Yes | 32K | ~4.7 tok/s | 18.2 GB |
| Q5_K_M | 18.4 GB | ✓ Yes | 32K | ~5.3 tok/s | 15.7 GB |
| Q4_K_M | 16.1 GB | ✓ Yes | 32K | ~6.2 tok/s | 13.4 GB |
| Q3_K_M | 12.1 GB | ✓ Yes | 32K | ~8.5 tok/s | 9.5 GB |
| Q2_K | 10 GB | ✓ Yes | 32K | ~10.7 tok/s | 7.3 GB |
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 Codestral on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, comfortably — Codestral 22B at Q5_K_M needs about 18.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~13.6 GB spare and running at ~5.3 tok/s (estimated), with room for about 32,768 tokens of context.
Which quantization of Codestral should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q5_K_M — it needs about 18.4 GB of the 32 GB available, downloads as roughly 15.7 GB, and runs at an estimated 5.3 tokens/sec with up to 32K of context.
What limits Codestral 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)
- Cogito v1 on Beelink SER9 (Ryzen AI 9, 32 GB)
- Command R Family on Beelink SER9 (Ryzen AI 9, 32 GB)
- Cosmos 3 on Beelink SER9 (Ryzen AI 9, 32 GB)
- DeepSeek-OCR on Beelink SER9 (Ryzen AI 9, 32 GB)
- DeepSeek R1 on Beelink SER9 (Ryzen AI 9, 32 GB)
Codestral on GPUs
- Codestral on NVIDIA GeForce RTX 5090
- Codestral on NVIDIA GeForce RTX 5080
- Codestral on NVIDIA GeForce RTX 5070 Ti
- Codestral on NVIDIA GeForce RTX 5070
What This Model Is Good At
Model & Tools
← Can I Run It? | Codestral model page | Check your hardware