Can a NVIDIA A100 (80GB) run Gemma 4 31B?

Yes — Gemma 4 31B runs at FP16 (61.4 GB) at about 23–34 tok/s on a NVIDIA A100 (80GB).

How much memory does Gemma 4 31B need?

Gemma 4 31B needs about 13.7 GB at 4K context at its smallest quantization. A NVIDIA A100 (80GB) has 80.0 GB.

Yes — Gemma 4 31B runs on a NVIDIA A100 (80GB) at FP16

Yes — it runs great.

Runs great

Best fit: Gemma 4 31B at FP16 · 61.4 GB weights · 23–34 tok/s on a NVIDIA A100 (80GB).

Arena Text Overall · style-controlled

1,452FP16 untested

gemma-4-31b · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry gemma-4-31b, 2026-10-08: reference rating 1,452.4. Published confidence bounds 1,444.9–1,459.8. 6,145 votes. Published gemma-4-31b 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: 63.4 GB; Weights + KV cache + runtime overhead
Estimated generation: 23–34 tok/s
Estimated first token: ~2.5s

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.

Gemma 4 31B quantizations on NVIDIA A100 (80GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	11.8 GB	13.7 GB	88–132 tok/s	Runs great
Q3_K_M	14.7 GB	16.7 GB	75–113 tok/s	Runs great
Q4_K_M	18.3 GB	20.3 GB	64–96 tok/s	Runs great
Q5_K_M	21.7 GB	23.6 GB	56–84 tok/s	Runs great
Q6_K	25.2 GB	27.2 GB	49–74 tok/s	Runs great
Q8_0	32.6 GB	34.6 GB	40–60 tok/s	Runs great
FP16	61.4 GB	63.4 GB	23–34 tok/s	Runs great

Open the full calculator →Everything a NVIDIA A100 (80GB) runs Gemma 4 31B on other machines What to buy to run it →

Ran Gemma 4 31B on a NVIDIA A100 (80GB)? Add your real numbers →