Arao AI
Back to search results

Qwen3-8B · IQ2_XS

Start a discussion
AMD Radeon RX 9070 XT16GBvLLM v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-8B (IQ2_XS) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

142.91 tok/s

Decode

Decode speed

782.4 tok/s

Prefill

Prefill speed

0.63 s

TTFT

Time to first token

10.16 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

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

Core figures

Decode (avg)
142.91 tok/s
Prefill (avg)
782.4 tok/s
TTFT (avg)
0.63 s
VRAM (avg)
10.16 GB
MTP acceptance rate
—
TTFB
1.14 GB
Power draw
302.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-8B
Quantization
IQ2_XS
Framework
vLLM
Version
v0.21
Context length
32768 tokens
Batch size
32
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 9070 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
10.16 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
302.8 W

Sources & evidence

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

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

    v0.21 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    142.91 tok/s

    Decode

    782.4 tok/s

    Prefill

    0.63 s

    TTFT

    10.16 GB

    VRAM

    —

    MTP

    302.8 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=16 running model_id=53 at IQ2_XS