Can I run this LLM?
Can a NVIDIA DGX Spark (GB10, 128GB) run LFM2.5 2.6B?
LFM · See model card · estimated for a 128.0 GB machine at 4K context.
Yes — it runs great.
Best fit: LFM2.5 2.6B at FP16 · 5.4 GB · 28–42 tok/s on a NVIDIA DGX Spark (GB10, 128GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q4_K_M | 1.7 GB | 66–98 tok/s | Runs great |
| Q5_K_M | 1.9 GB | 60–90 tok/s | Runs great |
| Q6_K | 2.2 GB | 55–82 tok/s | Runs great |
| Q8_0 | 2.9 GB | 46–69 tok/s | Runs great |
| FP16 | 5.4 GB | 28–42 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsLFM2.5 2.6B on other machinesWhat to buy to run it →
Ran LFM2.5 2.6B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →