Can I Run Nemotron Cascade 2 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes
Yes — Nemotron-Cascade 2 30B-A3B at Q6_K needs about 28.5 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~3.5 GB spare), at ~22.6 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q6_K · Estimated speed: ~22.6 tok/s
See what else this hardware can run →
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) |
Nemotron Cascade 2 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 65.8 GB | ✗ No | — | — | 63.2 GB |
| Q8_0 | 36.2 GB | ✗ No | — | — | 33.6 GB |
| Q6_K | 28.5 GB | ✓ Yes | 16K | ~22.6 tok/s | 25.9 GB |
| Q5_K_M | 25 GB | ✓ Yes | 32K | ~25.1 tok/s | 22.4 GB |
| Q4_K_M | 21.7 GB | ✓ Yes | 32K | ~27.9 tok/s | 19.1 GB |
| Q3_K_M | 16.1 GB | ✓ Yes | 64K | ~34.6 tok/s | 13.5 GB |
| Q2_K | 13 GB | ✓ Yes | 64K | ~39.8 tok/s | 10.4 GB |
Which Nemotron Cascade 2 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Nemotron Cascade 2 70B | 45.4 GB | ✗ Too large | — |
| Nemotron-Cascade 2 30B-A3B | 21.7 GB | ✓ Fits | ~27.9 tok/s |
What to watch out for
- 1 larger variant of Nemotron Cascade 2 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 Nemotron Cascade 2 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes — Nemotron-Cascade 2 30B-A3B at Q6_K needs about 28.5 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~3.5 GB spare), at ~22.6 tok/s (estimated), with room for about 16,384 tokens of context.
Which quantization of Nemotron Cascade 2 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q6_K — it needs about 28.5 GB of the 32 GB available, downloads as roughly 25.9 GB, and runs at an estimated 22.6 tokens/sec with up to 16K of context.
What limits Nemotron Cascade 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 Models on Beelink SER9 (Ryzen AI 9, 32 GB)
- Nex-N2 on Beelink SER9 (Ryzen AI 9, 32 GB)
- Nex-N2.5 on Beelink SER9 (Ryzen AI 9, 32 GB)
- North Mini Code on Beelink SER9 (Ryzen AI 9, 32 GB)
- OLMo 2 on Beelink SER9 (Ryzen AI 9, 32 GB)
- Phi 3.5 Family on Beelink SER9 (Ryzen AI 9, 32 GB)
Nemotron Cascade 2 on GPUs
- Nemotron Cascade 2 on NVIDIA GeForce RTX 5090
- Nemotron Cascade 2 on NVIDIA GeForce RTX 5080
- Nemotron Cascade 2 on NVIDIA GeForce RTX 5070 Ti
- Nemotron Cascade 2 on NVIDIA GeForce RTX 5070
What This Model Is Good At
Model & Tools
← Can I Run It? | Nemotron Cascade 2 model page | Check your hardware