Skip to content
can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA DGX Spark (GB10, 128GB) run Qwen3 32B?

Qwen · Apache 2.0 · estimated for a 128.0 GB machine at 4K context.

Yes — it runs great.

Runs great

Best fit: Qwen3 32B at Q2_K · 12.3 GB weights · 13–19 tok/s on a NVIDIA DGX Spark (GB10, 128GB).

Arena Text Overall · style-controlled

1,347Q2_K untested

qwen3-32b · published configuration reference · Q2_K 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 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
14.2 GB
Weights + KV cache + runtime overhead
Estimated generation
13–19 tok/s
Estimated first token
~8.0s

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 DGX Spark (GB10, 128GB), estimated at 4K context. Weights and total memory are shown separately.
QuantWeightsTotal memorySpeedFit
Q2_K12.3 GB14.2 GB13–19 tok/sRuns great
Q3_K_M16.0 GB17.8 GB10–15 tok/sTight / slow
Q4_K_M19.8 GB21.6 GB8–13 tok/sTight / slow
Q5_K_M23.2 GB25.1 GB7–11 tok/sTight / slow
Q6_K26.9 GB28.8 GB6–10 tok/sTight / slow
Q8_034.8 GB36.7 GB5–7 tok/sTight / slow
FP1665.5 GB67.4 GB3–4 tok/sTight / slow
Open the full calculator →Everything a NVIDIA DGX Spark (GB10, 128GB) runsQwen3 32B on other machinesWhat to buy to run it →

Ran Qwen3 32B on a NVIDIA DGX Spark (GB10, 128GB)? Add your real numbers →