Arao AI
Back to search results

Qwen2.5-Omni-3B · Q2_K

Start a discussion
AMD Radeon RX 9070 XT16GBStrata v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q2_K) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

287.44 tok/s

Decode

Decode speed

1,250.58 tok/s

Prefill

Prefill speed

1.67 s

TTFT

Time to first token

5.57 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 · IQ3_S Decode 181.8 · Prefill 969.43 ·
  2. llama.cpp · Q3_K_M Decode 169.43 · Prefill 689.96 ·
  3. Strata · Q2_K (current)Decode 287.44 · Prefill 1250.58 ·

Core figures

Decode (avg)
287.44 tok/s
Prefill (avg)
1,250.58 tok/s
TTFT (avg)
1.67 s
VRAM (avg)
5.57 GB
MTP acceptance rate
0.61
TTFB
2.3 GB
Power draw
303.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
Q2_K
Framework
Strata
Version
v0.22
Context length
2048 tokens
Batch size
256
GPU layers
5
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)
5.57 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
303.2 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

    v0.22 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    287.44 tok/s

    Decode

    1,250.58 tok/s

    Prefill

    1.67 s

    TTFT

    5.57 GB

    VRAM

    0.61

    MTP

    303.2 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=16 running model_id=60 at Q2_K