Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
NVIDIA H100 80GB HBM380GBvLLM v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

335.51 tok/s

Decode

Decode speed

1,078.48 tok/s

Prefill

Prefill speed

0.6 s

TTFT

Time to first token

9.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · IQ1_S (current)Decode 335.51 · Prefill 1078.48 ·
  2. Ollama · Q6_K Decode 301.71 · Prefill 1324.79 ·

Core figures

Decode (avg)
335.51 tok/s
Prefill (avg)
1,078.48 tok/s
TTFT (avg)
0.6 s
VRAM (avg)
9.16 GB
MTP acceptance rate
—
TTFB
2.68 GB
Power draw
581.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
vLLM
Version
v0.38
Context length
8192 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)
9.16 GB
OS
Ubuntu 22.04
Driver
570.86
CUDA
12.8
Power draw
581.8 W

Sources & evidence

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

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

    v0.38 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx

    335.51 tok/s

    Decode

    1,078.48 tok/s

    Prefill

    0.6 s

    TTFT

    9.16 GB

    VRAM

    —

    MTP

    581.8 W

    Power draw

    L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=53 at IQ1_S