Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q5_K_M

Start a discussion
AMD Radeon RX 7800 XT16GBStrata v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q5_K_M) on AMD Radeon RX 7800 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

122.13 tok/s

Decode

Decode speed

641.14 tok/s

Prefill

Prefill speed

2.07 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. Strata · Q3_K_S Decode 167.4 · Prefill 757.67 ·
  2. Strata · Q5_K_M (current)Decode 122.13 · Prefill 641.14 ·

Core figures

Decode (avg)
122.13 tok/s
Prefill (avg)
641.14 tok/s
TTFT (avg)
2.07 s
VRAM (avg)
9.91 GB
MTP acceptance rate
0.49
TTFB
0.98 GB
Power draw
317.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q5_K_M
Framework
Strata
Version
v0.27
Context length
8192 tokens
Batch size
512
GPU layers
15
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 7800 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
9.91 GB
OS
Ubuntu 22.04
Driver
amdgpu 6.10
CUDA
N/A
Power draw
317.7 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

    v0.27 · Ubuntu 22.04 · CUDA N/A · 8192 ctx

    122.13 tok/s

    Decode

    641.14 tok/s

    Prefill

    2.07 s

    TTFT

    9.91 GB

    VRAM

    0.49

    MTP

    317.7 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=31 running model_id=57 at Q5_K_M