Arao AI
Back to search results

Qwen3-4B · IQ4_XS

Start a discussion
AMD Radeon RX 907016GBStrata v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ4_XS) on AMD Radeon RX 9070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

168.75 tok/s

Decode

Decode speed

844.33 tok/s

Prefill

Prefill speed

0.88 s

TTFT

Time to first token

8.32 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 · Q2_K Decode 140.23 · Prefill 653.54 ·
  2. llama.cpp · Q8_0 Decode 73.3 · Prefill 246.97 ·
  3. Strata · IQ4_XS (current)Decode 168.75 · Prefill 844.33 ·

Core figures

Decode (avg)
168.75 tok/s
Prefill (avg)
844.33 tok/s
TTFT (avg)
0.88 s
VRAM (avg)
8.32 GB
MTP acceptance rate
0.61
TTFB
1.35 GB
Power draw
231.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ4_XS
Framework
Strata
Version
v0.52
Context length
16384 tokens
Batch size
1024
GPU layers
8
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
Nominal VRAM
16 GB
Measured VRAM (avg)
8.32 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
231.3 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

    v0.52 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    168.75 tok/s

    Decode

    844.33 tok/s

    Prefill

    0.88 s

    TTFT

    8.32 GB

    VRAM

    0.61

    MTP

    231.3 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=21 running model_id=54 at IQ4_XS