Can I Run Codestral on Beelink SER9 (Ryzen AI 9, 32 GB)?

Superseded model. Codestral has been superseded by Devstral. This page is kept for reference; the newer family is a better starting point. View Devstral →

Written by Jakub Rusinowski · Last updated May 29, 2024

Yes

Yes — Codestral 22B at Q8_0 needs about 26.3 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~5.7 GB spare), at ~7.7 tok/s (estimated), with room for about 32,768 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~7.7 tok/s

Beelink SER9 (Ryzen AI 9, 32 GB) — what it gives a model

Usable memory for models	32 GB
Memory bandwidth	256 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	~7.7 tok/s	23.6 GB
Q6_K	20.9 GB	✓ Yes	32K	~9.8 tok/s	18.2 GB
Q5_K_M	18.4 GB	✓ Yes	32K	~11.2 tok/s	15.7 GB
Q4_K_M	16.1 GB	✓ Yes	32K	~13 tok/s	13.4 GB
Q3_K_M	12.1 GB	✓ Yes	32K	~17.7 tok/s	9.5 GB
Q2_K	10 GB	✓ Yes	32K	~22.1 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 256 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