Can I run this LLM?
Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run LFM2.5 8B-A1B (MoE)?
LFM · See model card · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: LFM2.5 8B-A1B (MoE) at FP16 · 17.0 GB · 199–298 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q4_K_M | 5.2 GB | 290–434 tok/s | Runs great |
| Q5_K_M | 6.0 GB | 280–420 tok/s | Runs great |
| Q6_K | 7.0 GB | 271–406 tok/s | Runs great |
| Q8_0 | 9.0 GB | 252–378 tok/s | Runs great |
| FP16 | 17.0 GB | 199–298 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX Pro 6000 Blackwell (96GB) runsLFM2.5 8B-A1B (MoE) on other machinesWhat to buy to run it →
Ran LFM2.5 8B-A1B (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →