Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ3_S

Start a discussion
AMD Radeon RX 9070 XT16GBStrata v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ3_S) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

358.46 tok/s

Decode

Decode speed

1,486.41 tok/s

Prefill

Prefill speed

0.75 s

TTFT

Time to first token

2.79 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 · Q5_K_S Decode 267.22 · Prefill 915.84 ·
  2. Strata · IQ2_M Decode 311.28 · Prefill 1001.12 ·
  3. Strata · IQ3_S (current)Decode 358.46 · Prefill 1486.41 ·

Core figures

Decode (avg)
358.46 tok/s
Prefill (avg)
1,486.41 tok/s
TTFT (avg)
0.75 s
VRAM (avg)
2.79 GB
MTP acceptance rate
0.53
TTFB
2.87 GB
Power draw
262.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ3_S
Framework
Strata
Version
v0.24
Context length
16384 tokens
Batch size
256
GPU layers
5
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 XT
Nominal VRAM
16 GB
Measured VRAM (avg)
2.79 GB
OS
Ubuntu 22.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
262.9 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

    v0.24 · Ubuntu 22.04 · CUDA N/A · 16384 ctx

    358.46 tok/s

    Decode

    1,486.41 tok/s

    Prefill

    0.75 s

    TTFT

    2.79 GB

    VRAM

    0.53

    MTP

    262.9 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=16 running model_id=59 at IQ3_S