Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q5_K_M

Start a discussion
AMD Radeon AI PRO R970032GBvLLM v0.49L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q5_K_M) on AMD Radeon AI PRO R9700 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

111.48 tok/s

Decode

Decode speed

571.17 tok/s

Prefill

Prefill speed

1.45 s

TTFT

Time to first token

9.91 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · Q4_K_S Decode 158.57 · Prefill 583.28 ·
  2. vLLM · Q5_K_M (current)Decode 111.48 · Prefill 571.17 ·

Core figures

Decode (avg)
111.48 tok/s
Prefill (avg)
571.17 tok/s
TTFT (avg)
1.45 s
VRAM (avg)
9.91 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
249.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q5_K_M
Framework
vLLM
Version
v0.49
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 AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
9.91 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
249.8 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

    v0.49 · Ubuntu 22.04 · CUDA N/A · 32768 ctx

    111.48 tok/s

    Decode

    571.17 tok/s

    Prefill

    1.45 s

    TTFT

    9.91 GB

    VRAM

    —

    MTP

    249.8 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=79 running model_id=57 at Q5_K_M