Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ4_XS

Start a discussion
NVIDIA RTX 508016GBvLLM v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ4_XS) on NVIDIA RTX 5080 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

224.27 tok/s

Decode

Decode speed

989.89 tok/s

Prefill

Prefill speed

0.59 s

TTFT

Time to first token

14.53 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. vLLM · IQ4_XS (current)Decode 224.27 · Prefill 989.89 ·
  2. Strata · IQ3_XS Decode 308.04 · Prefill 1362.37 ·
  3. Strata · Q3_K_S Decode 323.81 · Prefill 1737.95 ·

Core figures

Decode (avg)
224.27 tok/s
Prefill (avg)
989.89 tok/s
TTFT (avg)
0.59 s
VRAM (avg)
14.53 GB
MTP acceptance rate
—
TTFB
1.79 GB
Power draw
249.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ4_XS
Framework
vLLM
Version
v0.26
Context length
2048 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 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
14.53 GB
OS
Windows 11 24H2
Driver
570.86
CUDA
13.0
Power draw
249.6 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-18

    v0.26 · Windows 11 24H2 · CUDA 13.0 · 2048 ctx

    224.27 tok/s

    Decode

    989.89 tok/s

    Prefill

    0.59 s

    TTFT

    14.53 GB

    VRAM

    —

    MTP

    249.6 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=14 running model_id=68 at IQ4_XS