Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ3_XS

Start a discussion
AMD Radeon RX 9070 GRE12GBOllama v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ3_XS) on AMD Radeon RX 9070 GRE with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

244.89 tok/s

Decode

Decode speed

1,100.19 tok/s

Prefill

Prefill speed

1.94 s

TTFT

Time to first token

2.75 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · IQ3_XS (current)Decode 244.89 · Prefill 1100.19 ·

Core figures

Decode (avg)
244.89 tok/s
Prefill (avg)
1,100.19 tok/s
TTFT (avg)
1.94 s
VRAM (avg)
2.75 GB
MTP acceptance rate
—
TTFB
1.96 GB
Power draw
287.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ3_XS
Framework
Ollama
Version
v0.21
Context length
2048 tokens
Batch size
256
GPU layers
99
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 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
2.75 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
287.7 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

    v0.21 · Ubuntu 24.04 · CUDA N/A · 2048 ctx

    244.89 tok/s

    Decode

    1,100.19 tok/s

    Prefill

    1.94 s

    TTFT

    2.75 GB

    VRAM

    —

    MTP

    287.7 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=32 running model_id=59 at IQ3_XS