Arao AI
Back to search results

Llama-3.1-8B-Instruct · Q3_K_S

Start a discussion
AMD Radeon RX 9070 XT16GBvLLM v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Llama-3.1-8B-Instruct (Q3_K_S) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

162.87 tok/s

Decode

Decode speed

574.19 tok/s

Prefill

Prefill speed

2.23 s

TTFT

Time to first token

13.02 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · IQ4_XS Decode 135.74 · Prefill 591.43 ·
  2. vLLM · Q3_K_S (current)Decode 162.87 · Prefill 574.19 ·
  3. vLLM · Q4_K_M Decode 144.21 · Prefill 558.74 ·

Core figures

Decode (avg)
162.87 tok/s
Prefill (avg)
574.19 tok/s
TTFT (avg)
2.23 s
VRAM (avg)
13.02 GB
MTP acceptance rate
—
TTFB
1.3 GB
Power draw
262.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Llama-3.1-8B-Instruct
Quantization
Q3_K_S
Framework
vLLM
Version
v0.23
Context length
32768 tokens
Batch size
8
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
AMD Radeon RX 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
13.02 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
12.6
Power draw
262.9 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

    v0.23 · Ubuntu 22.04 · CUDA 12.6 · 32768 ctx

    162.87 tok/s

    Decode

    574.19 tok/s

    Prefill

    2.23 s

    TTFT

    13.02 GB

    VRAM

    —

    MTP

    262.9 W

    Power draw

    L2 batch seed 2026-10-18: vLLM on hw_id=16 running model_id=68 at Q3_K_S