Can a NVIDIA B200 (192GB) run Qwen3 32B?

Yes — Qwen3 32B runs at FP16 (65.5 GB) at about 71–107 tok/s on a NVIDIA B200 (192GB).

How much memory does Qwen3 32B need?

Qwen3 32B needs about 14.2 GB at 4K context at its smallest quantization. A NVIDIA B200 (192GB) has 192.0 GB.

Yes — Qwen3 32B runs on a NVIDIA B200 (192GB) at FP16

Yes — it runs great.

Runs great

Best fit: Qwen3 32B at FP16 · 65.5 GB weights · 71–107 tok/s on a NVIDIA B200 (192GB).

Arena Text Overall · style-controlled

1,347FP16 untested

qwen3-32b · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry qwen3-32b, 2026-10-08: reference rating 1,346.9. Published confidence bounds 1,337.4–1,356.3. 3,926 votes. Published qwen3-32b 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: 67.4 GB; Weights + KV cache + runtime overhead
Estimated generation: 71–107 tok/s
Estimated first token: ~0.7s

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.

Qwen3 32B quantizations on NVIDIA B200 (192GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	12.3 GB	14.2 GB	200–300 tok/s	Runs great
Q3_K_M	16.0 GB	17.8 GB	178–267 tok/s	Runs great
Q4_K_M	19.8 GB	21.6 GB	160–240 tok/s	Runs great
Q5_K_M	23.2 GB	25.1 GB	146–219 tok/s	Runs great
Q6_K	26.9 GB	28.8 GB	134–201 tok/s	Runs great
Q8_0	34.8 GB	36.7 GB	114–170 tok/s	Runs great
FP16	65.5 GB	67.4 GB	71–107 tok/s	Runs great

Open the full calculator →Everything a NVIDIA B200 (192GB) runs Qwen3 32B on other machines What to buy to run it →

Ran Qwen3 32B on a NVIDIA B200 (192GB)? Add your real numbers →