Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ2_M

Start a discussion
AMD Radeon RX 9070 XT16GBStrata v0.21L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ2_M) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

311.28 tok/s

Decode

Decode speed

1,001.12 tok/s

Prefill

Prefill speed

1.8 s

TTFT

Time to first token

2.65 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 (current)Decode 311.28 · Prefill 1001.12 ·
  3. Strata · IQ3_S Decode 358.46 · Prefill 1486.41 ·

Core figures

Decode (avg)
311.28 tok/s
Prefill (avg)
1,001.12 tok/s
TTFT (avg)
1.8 s
VRAM (avg)
2.65 GB
MTP acceptance rate
0.58
TTFB
2.49 GB
Power draw
259.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ2_M
Framework
Strata
Version
v0.21
Context length
16384 tokens
Batch size
1024
GPU layers
15
Flash Attention
On

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)
2.65 GB
OS
Windows 11 23H2
Driver
amdgpu 6.11
CUDA
N/A
Power draw
259.9 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

    v0.21 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    311.28 tok/s

    Decode

    1,001.12 tok/s

    Prefill

    1.8 s

    TTFT

    2.65 GB

    VRAM

    0.58

    MTP

    259.9 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=16 running model_id=59 at IQ2_M