Can I run this LLM?
Can a NVIDIA A100 (80GB) run Mistral Small 3.2 24B?
Mistral · Apache 2.0 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Runs greatBest fit: Mistral Small 3.2 24B at FP16 · 47.2 GB weights · 29–43 tok/s on a NVIDIA A100 (80GB).
Arena Text Overall · style-controlled
1,356FP16 untestedmistral-small-2506 · published configuration reference · FP16 not tested
Arena Text Overall (style-controlled), exact published entry mistral-small-2506, 2026-10-08: reference rating 1,356.2. Published confidence bounds 1,351–1,361.5. 17,466 votes. Published mistral-small-2506 configuration reference. Reasoning mode is not disclosed by the Arena dataset. Tested precision, runtime and sampling settings are not disclosed in this dataset. Selected FP16 has not been measured by this Arena entry. No quantization quality adjustment is applied.
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
- 48.6 GB
- Weights + KV cache + runtime overhead
- Estimated generation
- 29–43 tok/s
- Estimated first token
- ~1.9s
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 | 8.9 GB | 10.4 GB | 110–165 tok/s | Runs great |
| Q3_K_M | 11.5 GB | 12.9 GB | 93–139 tok/s | Runs great |
| Q4_K_M | 14.3 GB | 15.8 GB | 79–118 tok/s | Runs great |
| Q5_K_M | 16.8 GB | 18.2 GB | 70–105 tok/s | Runs great |
| Q6_K | 19.4 GB | 20.8 GB | 62–94 tok/s | Runs great |
| Q8_0 | 25.1 GB | 26.5 GB | 50–76 tok/s | Runs great |
| FP16 | 47.2 GB | 48.6 GB | 29–43 tok/s | Runs great |
Ran Mistral Small 3.2 24B on a NVIDIA A100 (80GB)? Add your real numbers →