Can I run this LLM?
Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Step 3.7 Flash (MoE)?
Step · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Step 3.7 Flash (MoE) at Q2_K · 71.2 GB · 169–254 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 71.2 GB | 169–254 tok/s | Runs great |
| Q3_K_M | 91.8 GB | 148–222 tok/s | Won't fit |
| Q4_K_M | 121.6 GB | 125–187 tok/s | Won't fit |
| Q5_K_M | 142.0 GB | 113–169 tok/s | Won't fit |
| Q6_K | 171.8 GB | 99–149 tok/s | Won't fit |
| Q8_0 | 212.0 GB | 85–127 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX Pro 6000 Blackwell (96GB) runsStep 3.7 Flash (MoE) on other machinesWhat to buy to run it →
Ran Step 3.7 Flash (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →