Can I Run GLM-6 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated June 26, 2026
Yes — comfortably
Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~20.4 GB spare and running at ~8.7 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~8.7 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) |
GLM-6 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 20 GB | ✓ Yes | 64K | ~4.8 tok/s | 18 GB |
| Q8_0 | 11.6 GB | ✓ Yes | 64K | ~8.7 tok/s | 9.6 GB |
| Q6_K | 9.4 GB | ✓ Yes | 64K | ~11 tok/s | 7.4 GB |
| Q5_K_M | 8.4 GB | ✓ Yes | 64K | ~12.5 tok/s | 6.4 GB |
| Q4_K_M | 7.4 GB | ✓ Yes | 64K | ~14.4 tok/s | 5.4 GB |
| Q3_K_M | 5.8 GB | ✓ Yes | 64K | ~19.4 tok/s | 3.8 GB |
| Q2_K | 5 GB | ✓ Yes | 64K | ~23.9 tok/s | 3 GB |
Which GLM-6 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GLM-6 355B-A32B | 219.2 GB | ✗ Too large | — |
| GLM-6 9B | 7.4 GB | ✓ Fits | ~14.4 tok/s |
What to watch out for
- 1 larger variant of GLM-6 does not fit and would need CPU offload or different hardware.
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
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 inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run GLM-6 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, comfortably — GLM-6 9B at Q8_0 needs about 11.6 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~20.4 GB spare and running at ~8.7 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of GLM-6 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q8_0 — it needs about 11.6 GB of the 32 GB available, downloads as roughly 9.6 GB, and runs at an estimated 8.7 tokens/sec with up to 64K of context.
What limits GLM-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)
- GPT-OSS 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)
GLM-6 on GPUs
- GLM-6 on NVIDIA GeForce RTX 5070
- GLM-6 on NVIDIA GeForce RTX 5060 Ti 8GB
- GLM-6 on NVIDIA GeForce RTX 5060
- GLM-6 on NVIDIA GeForce RTX 4070 Ti