Arao AI
Back to search results

Llama-3.1-8B-Instruct · IQ4_XS

Start a discussion
AMD Radeon RX 7900 XTX24GBvLLM v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (IQ4_XS) on AMD Radeon RX 7900 XTX with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

91.85 tok/s

Decode

Decode speed

357.41 tok/s

Prefill

Prefill speed

1.87 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 91.85 · Prefill 357.41 ·
  2. Strata · IQ4_XS Decode 138.01 · Prefill 527.22 ·

Core figures

Decode (avg)
91.85 tok/s
Prefill (avg)
357.41 tok/s
TTFT (avg)
1.87 s
VRAM (avg)
14.53 GB
MTP acceptance rate
—
TTFB
0.73 GB
Power draw
240.6 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
IQ4_XS
Framework
vLLM
Version
v0.41
Context length
32768 tokens
Batch size
16
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
AMD Radeon RX 7900 XTX
Nominal VRAM
24 GB
Measured VRAM (avg)
14.53 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.6
Power draw
240.6 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

    v0.41 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx

    91.85 tok/s

    Decode

    357.41 tok/s

    Prefill

    1.87 s

    TTFT

    14.53 GB

    VRAM

    —

    MTP

    240.6 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=11 running model_id=68 at IQ4_XS