Arao AI
Back to search results

Qwen2.5-Omni-3B · Q5_K_M

Start a discussion
AMD Radeon RX 9070 GRE12GBStrata v0.33L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q5_K_M) on AMD Radeon RX 9070 GRE with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

128.98 tok/s

Decode

Decode speed

579.29 tok/s

Prefill

Prefill speed

0.52 s

TTFT

Time to first token

7.96 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Strata · Q5_K_M (current)Decode 128.98 · Prefill 579.29 ·

Core figures

Decode (avg)
128.98 tok/s
Prefill (avg)
579.29 tok/s
TTFT (avg)
0.52 s
VRAM (avg)
7.96 GB
MTP acceptance rate
0.55
TTFB
1.03 GB
Power draw
236.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
Q5_K_M
Framework
Strata
Version
v0.33
Context length
16384 tokens
Batch size
1024
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 GRE
Nominal VRAM
12 GB
Measured VRAM (avg)
7.96 GB
OS
Ubuntu 24.04
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
236.8 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

    v0.33 · Ubuntu 24.04 · CUDA N/A · 16384 ctx

    128.98 tok/s

    Decode

    579.29 tok/s

    Prefill

    0.52 s

    TTFT

    7.96 GB

    VRAM

    0.55

    MTP

    236.8 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=32 running model_id=60 at Q5_K_M