Arao AI
Back to search results

Qwen3-8B · Q4_K_S

Start a discussion
AMD Radeon RX 9070 XT16GBllama.cpp v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (Q4_K_S) on AMD Radeon RX 9070 XT with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

123.04 tok/s

Decode

Decode speed

487.34 tok/s

Prefill

Prefill speed

1.3 s

TTFT

Time to first token

15.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. llama.cpp · Q4_K_S (current)Decode 123.04 · Prefill 487.34 ·
  2. vLLM · Q2_K Decode 168.21 · Prefill 814.55 ·
  3. vLLM · IQ2_XS Decode 142.91 · Prefill 782.4 ·
  4. Strata · IQ2_XS Decode 192.63 · Prefill 774.46 ·

Core figures

Decode (avg)
123.04 tok/s
Prefill (avg)
487.34 tok/s
TTFT (avg)
1.3 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.98 GB
Power draw
255.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.23
Context length
8192 tokens
Batch size
512
GPU layers
20
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)
15.2 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
12.8
Power draw
255.8 W

Sources & evidence

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

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

    v0.23 · Ubuntu 24.04 · CUDA 12.8 · 8192 ctx

    123.04 tok/s

    Decode

    487.34 tok/s

    Prefill

    1.3 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    255.8 W

    Power draw

    L2 batch seed 2026-10-18: llama.cpp on hw_id=16 running model_id=53 at Q4_K_S