Can I run this LLM?
Can a NVIDIA L40S (48GB) run NVIDIA Nemotron 3.5 Bolt 74B A9B?
Nemotron · See model card · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: NVIDIA Nemotron 3.5 Bolt 74B A9B at Q2_K · 28.8 GB weights · 121–182 tok/s on a NVIDIA L40S (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
- 29.6 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 121–182 tok/s
- Estimated first token
- ~1.2s
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 | 28.8 GB | 29.6 GB | 121–182 tok/s | Runs great |
| Q3_K_M | 39.0 GB | 39.9 GB | 98–147 tok/s | Tight / slow |
| Q4_K_M | 50.2 GB | 51.1 GB | — not resident | Won't fit |
| Q5_K_M | 58.9 GB | 59.7 GB | — not resident | Won't fit |
| Q6_K | 72.4 GB | 73.2 GB | — not resident | Won't fit |
| Q8_0 | 78.9 GB | 79.7 GB | — not resident | Won't fit |
| FP16 | 148.2 GB | 149.0 GB | — not resident | Won't fit |
Ran NVIDIA Nemotron 3.5 Bolt 74B A9B on a NVIDIA L40S (48GB)? Add your real numbers →