Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q5_K_S

Start a discussion
AMD Strix Point (Radeon 890M)vLLM v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q5_K_S) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

60.14 tok/s

Decode

Decode speed

291.94 tok/s

Prefill

Prefill speed

2.23 s

TTFT

Time to first token

9.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ4_XS Decode 75.65 · Prefill 261.83 ·
  2. vLLM · Q5_K_S (current)Decode 60.14 · Prefill 291.94 ·

Core figures

Decode (avg)
60.14 tok/s
Prefill (avg)
291.94 tok/s
TTFT (avg)
2.23 s
VRAM (avg)
9.66 GB
MTP acceptance rate
—
TTFB
0.48 GB
Power draw
48.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q5_K_S
Framework
vLLM
Version
v0.51
Context length
16384 tokens
Batch size
8
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 Strix Point (Radeon 890M)
Measured VRAM (avg)
9.66 GB
OS
Ubuntu 22.04
Driver
555.85
CUDA
N/A
Power draw
48.3 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.51 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    60.14 tok/s

    Decode

    291.94 tok/s

    Prefill

    2.23 s

    TTFT

    9.66 GB

    VRAM

    —

    MTP

    48.3 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=57 at Q5_K_S