Arao AI
Back to search results

Qwen3.8-27B · Q5_K_M

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.8-27B (Q5_K_M) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

206.52 tok/s

Decode

Decode speed

1,029.93 tok/s

Prefill

Prefill speed

0.84 s

TTFT

Time to first token

54.83 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. vLLM · Q4_K_M Decode 224.13 · Prefill 1208.86 ·
  2. vLLM · Q5_K_M (current)Decode 206.52 · Prefill 1029.93 ·
  3. Strata · IQ2_M Decode 325.92 · Prefill 1772.8 ·

Core figures

Decode (avg)
206.52 tok/s
Prefill (avg)
1,029.93 tok/s
TTFT (avg)
0.84 s
VRAM (avg)
54.83 GB
MTP acceptance rate
—
TTFB
1.65 GB
Power draw
589.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-27B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.41
Context length
4096 tokens
Batch size
8
GPU layers
999
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA H100 80GB HBM3
Nominal VRAM
80 GB
Measured VRAM (avg)
54.83 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.8
Power draw
589.1 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.41 · Ubuntu 24.04 · CUDA 12.8 · 4096 ctx

    206.52 tok/s

    Decode

    1,029.93 tok/s

    Prefill

    0.84 s

    TTFT

    54.83 GB

    VRAM

    —

    MTP

    589.1 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=5 at Q5_K_M