Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q4_K_S

Start a discussion
AMD Strix Point (Radeon 890M)llama.cpp v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q4_K_S) on AMD Strix Point (Radeon 890M) with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

160.41 tok/s

Decode

Decode speed

865.77 tok/s

Prefill

Prefill speed

1.45 s

TTFT

Time to first token

2.92 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 · Q4_K_S (current)Decode 160.41 · Prefill 865.77 ·
  2. Strata · Q4_K_S Decode 231.08 · Prefill 1081.57 ·

Core figures

Decode (avg)
160.41 tok/s
Prefill (avg)
865.77 tok/s
TTFT (avg)
1.45 s
VRAM (avg)
2.92 GB
MTP acceptance rate
—
TTFB
1.28 GB
Power draw
53.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.48
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

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)
2.92 GB
OS
macOS 15.0
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
53.4 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

    v0.48 · macOS 15.0 · CUDA N/A · 4096 ctx

    160.41 tok/s

    Decode

    865.77 tok/s

    Prefill

    1.45 s

    TTFT

    2.92 GB

    VRAM

    —

    MTP

    53.4 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=89 running model_id=59 at Q4_K_S