Can I Run LFM2.5 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Written by Jakub Rusinowski · Last updated October 15, 2026
Yes
Yes — LFM2.5-24B-A2B at Q8_0 needs about 26.5 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~5.5 GB spare), at ~31.2 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~31.2 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) |
LFM2.5 on Beelink SER9 (Ryzen AI 9, 32 GB): memory by quantization
| Quant | Memory needed | Fits 32 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 48.9 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 26.5 GB | ✓ Yes | 128K | ~31.2 tok/s | 25.5 GB |
| Q6_K | 20.7 GB | ✓ Yes | 128K | ~39.2 tok/s | 19.7 GB |
| Q5_K_M | 18 GB | ✓ Yes | 128K | ~44.5 tok/s | 17 GB |
| Q4_K_M | 15.5 GB | ✓ Yes | 128K | ~51 tok/s | 14.5 GB |
| Q3_K_M | 11.2 GB | ✓ Yes | 128K | ~67.7 tok/s | 10.2 GB |
| Q2_K | 8.8 GB | ✓ Yes | 128K | ~82.5 tok/s | 7.9 GB |
Which LFM2.5 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| LFM2.5-24B-A2B | 15.5 GB | ✓ Fits | ~51 tok/s |
| LFM2.5-8B-A1B | 7 GB | ✓ Fits | ~53.1 tok/s |
| LFM2.5 2.6B | 3.2 GB | ✓ Fits | ~40.4 tok/s |
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 LFM2.5 on Beelink SER9 (Ryzen AI 9, 32 GB)?
Yes — LFM2.5-24B-A2B at Q8_0 needs about 26.5 GB of the 32 GB usable on Beelink SER9 (Ryzen AI 9, 32 GB) (~5.5 GB spare), at ~31.2 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of LFM2.5 should I use on Beelink SER9 (Ryzen AI 9, 32 GB)?
Q8_0 — it needs about 26.5 GB of the 32 GB available, downloads as roughly 25.5 GB, and runs at an estimated 31.2 tokens/sec with up to 128K of context.
What limits LFM2.5 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 3.1 Family on Beelink SER9 (Ryzen AI 9, 32 GB)
- Llama 3.2 Family on Beelink SER9 (Ryzen AI 9, 32 GB)
- Llama 3.2 Vision 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)
LFM2.5 on GPUs
- LFM2.5 on NVIDIA GeForce RTX 5070
- LFM2.5 on NVIDIA GeForce RTX 5060 Ti 8GB
- LFM2.5 on NVIDIA GeForce RTX 5060
- LFM2.5 on NVIDIA GeForce RTX 4070 Ti