Can a NVIDIA RTX 3060 (12GB) run Mistral Small 3.2 24B?

Just about — Mistral Small 3.2 24B runs at Q2_K (8.9 GB) at about 26–39 tok/s on a NVIDIA RTX 3060 (12GB).

How much memory does Mistral Small 3.2 24B need?

Mistral Small 3.2 24B needs about 10.4 GB at 4K context at its smallest quantization. A NVIDIA RTX 3060 (12GB) has 12.0 GB.

Tight fit: Mistral Small 3.2 24B on a NVIDIA RTX 3060 (12GB) at Q2_K

Yes, but it's tight.

Tight / slow

Best fit: Mistral Small 3.2 24B at Q2_K · 8.9 GB weights · 26–39 tok/s on a NVIDIA RTX 3060 (12GB).

Arena Text Overall · style-controlled

1,356Q2_K untested

mistral-small-2506 · published configuration reference · Q2_K 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 Q2_K 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: 10.4 GB; Weights + KV cache + runtime overhead
Estimated generation: 26–39 tok/s
Estimated first token: ~22s

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.

Mistral Small 3.2 24B quantizations on NVIDIA RTX 3060 (12GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	8.9 GB	10.4 GB	26–39 tok/s	Tight / slow
Q3_K_M	11.5 GB	12.9 GB	— not resident	Won't fit
Q4_K_M	14.3 GB	15.8 GB	— not resident	Won't fit
Q5_K_M	16.8 GB	18.2 GB	— not resident	Won't fit
Q6_K	19.4 GB	20.8 GB	— not resident	Won't fit
Q8_0	25.1 GB	26.5 GB	— not resident	Won't fit
FP16	47.2 GB	48.6 GB	— not resident	Won't fit

Open the full calculator →Everything a NVIDIA RTX 3060 (12GB) runs Mistral Small 3.2 24B on other machines What to buy to run it →

Ran Mistral Small 3.2 24B on a NVIDIA RTX 3060 (12GB)? Add your real numbers →