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.
Tight / slowBest fit: Mistral Small 4 119B (MoE) at Q2_K · 40.2 GB weights · 168–252 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Arena Text Overall · style-controlled
UnratedNo exact matchNo reviewed exact Arena match
No reviewed exact model/configuration match in the Arena Text Overall style-controlled snapshot. No family or editorial score is substituted. Local quantization quality is unmeasured.
Snapshot published 2026-10-08 · snapshot imported 2026-10-11 UTC · validated last-good data · manual refresh
Arena leaderboard dataset · Arena / lmarena-ai, Arena Leaderboard Dataset (CC BY 4.0). Selected Text Overall style-controlled rows; field names adapted, ratings unchanged. · dataset CC BY 4.0 · revision e16f90232986
- Total memory at 4K context
- 41.1 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 168–252 tok/s
- Estimated first token
- ~0.9s
Every quantization on this machine
On small screens, each quant lists every metric below its name. On wider screens, scroll sideways for total memory, speed and fit. Keyboard: focus the table, then use the arrow keys. Quant names stay visible.
| Quant | Weights | Total memory | Speed | Fit |
|---|---|---|---|---|
| Q2_K | 40.2 GB | 41.1 GB | 168–252 tok/s | Tight / slow |
| Q3_K_M | 54.4 GB | 55.3 GB | — not resident | Won't fit |
| Q4_K_M | 73.8 GB | 74.7 GB | — not resident | Won't fit |
| Q5_K_M | 89.2 GB | 90.1 GB | — not resident | Won't fit |
| Q6_K | 99.4 GB | 100.3 GB | — not resident | Won't fit |
| Q8_0 | 126.5 GB | 127.4 GB | — not resident | Won't fit |
| FP16 | 238.0 GB | 238.9 GB | — not resident | Won't fit |
Ran Mistral Small 4 119B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →