Can I Run Llama 3.2 Vision on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated September 25, 2024
Yes — comfortably
Yes, comfortably — Llama 3.2 Vision 11B at Q8_0 needs about 13.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~18.6 GB spare and running at ~7.4 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~7.4 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) |
Llama 3.2 Vision on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 23.3 GB | ✓ Yes | 32K | ~4.1 tok/s | 21.2 GB |
| Q8_0 | 13.4 GB | ✓ Yes | 64K | ~7.4 tok/s | 11.3 GB |
| Q6_K | 10.8 GB | ✓ Yes | 64K | ~9.4 tok/s | 8.7 GB |
| Q5_K_M | 9.7 GB | ✓ Yes | 64K | ~10.7 tok/s | 7.5 GB |
| Q4_K_M | 8.5 GB | ✓ Yes | 64K | ~12.4 tok/s | 6.4 GB |
| Q3_K_M | 6.7 GB | ✓ Yes | 64K | ~16.7 tok/s | 4.5 GB |
| Q2_K | 5.6 GB | ✓ Yes | 64K | ~20.7 tok/s | 3.5 GB |
Which Llama 3.2 Vision sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Llama 3.2 Vision 90B | 57.8 GB | ✗ Too large | — |
| Llama 3.2 Vision 11B | 8.5 GB | ✓ Fits | ~12.4 tok/s |
What to watch out for
- 1 larger variant of Llama 3.2 Vision 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 Llama 3.2 Vision on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes, comfortably — Llama 3.2 Vision 11B at Q8_0 needs about 13.4 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB), leaving ~18.6 GB spare and running at ~7.4 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of Llama 3.2 Vision should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q8_0 — it needs about 13.4 GB of the 32 GB available, downloads as roughly 11.3 GB, and runs at an estimated 7.4 tokens/sec with up to 64K of context.
What limits Llama 3.2 Vision 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)
- Llama 3.3 on Beelink SER9 (Ryzen AI 9, 32 GB)
- Magistral Small on Beelink SER9 (Ryzen AI 9, 32 GB)
- MiniCPM-V on Beelink SER9 (Ryzen AI 9, 32 GB)
- Ministral on Beelink SER9 (Ryzen AI 9, 32 GB)
- Ministral 3 on Beelink SER9 (Ryzen AI 9, 32 GB)
Llama 3.2 Vision on GPUs
- Llama 3.2 Vision on NVIDIA GeForce RTX 5070
- Llama 3.2 Vision on NVIDIA GeForce RTX 5060 Ti 8GB
- Llama 3.2 Vision on NVIDIA GeForce RTX 5060
- Llama 3.2 Vision on NVIDIA GeForce RTX 4070 Ti
What This Model Is Good At
Model & Tools
← Can I Run It? | Llama 3.2 Vision model page | Check your hardware