Arao AI
Back to search results

Qwen3-8B · IQ1_S

Start a discussion
NVIDIA RTX 308010GBvLLM v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on NVIDIA RTX 3080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

114 tok/s

Decode

Decode speed

526.44 tok/s

Prefill

Prefill speed

0.4 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

5 days ago

Last verified

Performance

  1. vLLM · IQ1_S (current)Decode 114 · Prefill 526.44 ·

Core figures

Decode (avg)
114 tok/s
Prefill (avg)
526.44 tok/s
TTFT (avg)
0.4 s
VRAM (avg)
9.16 GB
MTP acceptance rate
—
TTFB
0.91 GB
Power draw
283.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ1_S
Framework
vLLM
Version
v0.45
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 RTX 3080
Nominal VRAM
10 GB
Measured VRAM (avg)
9.16 GB
OS
macOS 15.0
Driver
565.57
CUDA
12.4
Power draw
283.3 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.45 · macOS 15.0 · CUDA 12.4 · 32768 ctx

    114 tok/s

    Decode

    526.44 tok/s

    Prefill

    0.4 s

    TTFT

    9.16 GB

    VRAM

    —

    MTP

    283.3 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=44 running model_id=53 at IQ1_S