Arao AI
Back to search results

Qwen3.6-27B · Q8_0

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.6-27B (Q8_0) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

234.17 tok/s

Decode

Decode speed

755.94 tok/s

Prefill

Prefill speed

1.52 s

TTFT

Time to first token

67.3 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 · Q8_0 (current)Decode 234.17 · Prefill 755.94 ·
  2. Strata · Q3_K_S Decode 335.33 · Prefill 1692.56 ·
  3. Strata · Q8_0 Decode 297.87 · Prefill 1046.41 ·

Core figures

Decode (avg)
234.17 tok/s
Prefill (avg)
755.94 tok/s
TTFT (avg)
1.52 s
VRAM (avg)
67.3 GB
MTP acceptance rate
—
TTFB
1.87 GB
Power draw
642.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.6-27B
Quantization
Q8_0
Framework
vLLM
Version
v0.46
Context length
32768 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

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)
67.3 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.8
Power draw
642.4 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

    v0.46 · Ubuntu 22.04 · CUDA 12.8 · 32768 ctx

    234.17 tok/s

    Decode

    755.94 tok/s

    Prefill

    1.52 s

    TTFT

    67.3 GB

    VRAM

    —

    MTP

    642.4 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=6 at Q8_0