Arao AI
Back to search results

Qwen2.5-Omni-3B · IQ4_XS

Start a discussion
AMD Radeon AI PRO R970032GBOllama v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (IQ4_XS) on AMD Radeon AI PRO R9700 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

178.25 tok/s

Decode

Decode speed

834.26 tok/s

Prefill

Prefill speed

2.2 s

TTFT

Time to first token

6.76 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 · IQ4_XS Decode 183.61 · Prefill 748.24 ·
  2. llama.cpp · Q2_K Decode 223.75 · Prefill 955.8 ·
  3. Ollama · IQ2_XS Decode 228.57 · Prefill 1151.43 ·
  4. Ollama · IQ4_XS (current)Decode 178.25 · Prefill 834.26 ·

Core figures

Decode (avg)
178.25 tok/s
Prefill (avg)
834.26 tok/s
TTFT (avg)
2.2 s
VRAM (avg)
6.76 GB
MTP acceptance rate
—
TTFB
1.43 GB
Power draw
303.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
IQ4_XS
Framework
Ollama
Version
v0.40
Context length
16384 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
AMD Radeon AI PRO R9700
Nominal VRAM
32 GB
Measured VRAM (avg)
6.76 GB
OS
Windows 11 23H2
Driver
amdgpu-pro 24.20
CUDA
N/A
Power draw
303.1 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

    v0.40 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    178.25 tok/s

    Decode

    834.26 tok/s

    Prefill

    2.2 s

    TTFT

    6.76 GB

    VRAM

    —

    MTP

    303.1 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=79 running model_id=60 at IQ4_XS