Can I run this LLM?
Can a NVIDIA B200 (192GB) run Ling 3.0 Flash (MoE)?
Ling · MIT · estimated for a 192.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Ling 3.0 Flash (MoE) at Q8_0 · 135.6 GB · 274–411 tok/s on a NVIDIA B200 (192GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 45.9 GB | 329–493 tok/s | Runs great |
| Q3_K_M | 59.0 GB | 319–479 tok/s | Runs great |
| Q4_K_M | 77.8 GB | 307–460 tok/s | Runs great |
| Q5_K_M | 90.7 GB | 299–448 tok/s | Runs great |
| Q6_K | 109.3 GB | 288–432 tok/s | Runs great |
| Q8_0 | 135.6 GB | 274–411 tok/s | Runs great |
| FP16 | 255.1 GB | 224–336 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA B200 (192GB) runsLing 3.0 Flash (MoE) on other machinesWhat to buy to run it →
Ran Ling 3.0 Flash (MoE) on a NVIDIA B200 (192GB)? Add your real numbers →