Arao AI
Back to search results

Qwen2.5-Omni-3B · IQ2_M

Start a discussion
AMD Strix Point (Radeon 890M)Ollama v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ2_M) on AMD Strix Point (Radeon 890M) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

98.85 tok/s

Decode

Decode speed

414.8 tok/s

Prefill

Prefill speed

1.51 s

TTFT

Time to first token

5.38 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · IQ2_M (current)Decode 98.85 · Prefill 414.8 ·
  2. Ollama · Q6_K Decode 60.33 · Prefill 317.9 ·
  3. Strata · IQ3_S Decode 128.16 · Prefill 598.86 ·

Core figures

Decode (avg)
98.85 tok/s
Prefill (avg)
414.8 tok/s
TTFT (avg)
1.51 s
VRAM (avg)
5.38 GB
MTP acceptance rate
—
TTFB
0.79 GB
Power draw
62.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
IQ2_M
Framework
Ollama
Version
v0.38
Context length
2048 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Strix Point (Radeon 890M)
Measured VRAM (avg)
5.38 GB
OS
Ubuntu 24.04
Driver
amdgpu 6.11
CUDA
N/A
Power draw
62.5 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.38 · Ubuntu 24.04 · CUDA N/A · 2048 ctx

    98.85 tok/s

    Decode

    414.8 tok/s

    Prefill

    1.51 s

    TTFT

    5.38 GB

    VRAM

    —

    MTP

    62.5 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=89 running model_id=60 at IQ2_M