Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Mistral Small 4 119B (MoE)?
Mistral · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes, but it's tight.
Best fit: Mistral Small 4 119B (MoE) at Q2_K · 40.2 GB · 168–252 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 40.2 GB | 168–252 tok/s | Tight / slow |
| Q3_K_M | 54.4 GB | 142–213 tok/s | Won't fit |
| Q4_K_M | 73.8 GB | 117–176 tok/s | Won't fit |
| Q5_K_M | 89.2 GB | 103–154 tok/s | Won't fit |
| Q6_K | 99.4 GB | 95–143 tok/s | Won't fit |
| Q8_0 | 126.5 GB | 79–119 tok/s | Won't fit |
| FP16 | 238.0 GB | 47–71 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsMistral Small 4 119B (MoE) on other machinesWhat to buy to run it →
Ran Mistral Small 4 119B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →