Can a NVIDIA H100 SXM (80GB) run Qwen3.8 27B?

Yes — Qwen3.8 27B runs at FP16 (54.7 GB) at about 40–60 tok/s on a NVIDIA H100 SXM (80GB).

How much memory does Qwen3.8 27B need?

Qwen3.8 27B needs about 11.9 GB at 4K context at its smallest quantization. A NVIDIA H100 SXM (80GB) has 80.0 GB.

Yes — Qwen3.8 27B runs on a NVIDIA H100 SXM (80GB) at FP16

Yes — it runs great.

Runs great

Best fit: Qwen3.8 27B at FP16 · 54.7 GB weights · 40–60 tok/s on a NVIDIA H100 SXM (80GB).

Arena Text Overall · style-controlled

1,438FP16 untested

qwen3.8-27b · published configuration reference · FP16 not tested

Arena Text Overall (style-controlled), exact published entry qwen3.8-27b, 2026-10-08: reference rating 1,438.1. Published confidence bounds 1,432.8–1,443.4. 20,711 votes. Published qwen3.8-27b 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: 55.7 GB; Weights + KV cache + runtime overhead
Estimated generation: 40–60 tok/s
Estimated first token: ~1.2s

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.

Qwen3.8 27B quantizations on NVIDIA H100 SXM (80GB), estimated at 4K context. Weights and total memory are shown separately.
Quant	Weights	Total memory	Speed	Fit
Q2_K	10.8 GB	11.9 GB	139–208 tok/s	Runs great
Q3_K_M	13.4 GB	14.5 GB	121–182 tok/s	Runs great
Q4_K_M	17.4 GB	18.5 GB	101–152 tok/s	Runs great
Q5_K_M	20.9 GB	22.0 GB	89–133 tok/s	Runs great
Q6_K	23.9 GB	24.9 GB	80–120 tok/s	Runs great
Q8_0	29.1 GB	30.2 GB	68–103 tok/s	Runs great
FP16	54.7 GB	55.7 GB	40–60 tok/s	Runs great

Open the full calculator →Everything a NVIDIA H100 SXM (80GB) runs Qwen3.8 27B on other machines What to buy to run it →

Ran Qwen3.8 27B on a NVIDIA H100 SXM (80GB)? Add your real numbers →