Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run MiMo V2.6 Distill Qwen 9B?
MiMo · MIT · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: MiMo V2.6 Distill Qwen 9B at FP16 · 17.9 GB · 35–53 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 3.6 GB | 124–186 tok/s | Runs great |
| Q3_K_M | 4.5 GB | 108–162 tok/s | Runs great |
| Q4_K_M | 5.8 GB | 90–134 tok/s | Runs great |
| Q5_K_M | 6.9 GB | 79–119 tok/s | Runs great |
| Q6_K | 7.8 GB | 72–108 tok/s | Runs great |
| Q8_0 | 9.6 GB | 61–92 tok/s | Runs great |
| FP16 | 17.9 GB | 35–53 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsMiMo V2.6 Distill Qwen 9B on other machinesWhat to buy to run it →
Ran MiMo V2.6 Distill Qwen 9B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →