Arao AI
Back to search results

Qwen2.5-Omni-3B · Q5_K_S

Start a discussion
Intel Arc 140VStrata v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q5_K_S) on Intel Arc 140V with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

92.36 tok/s

Decode

Decode speed

496.83 tok/s

Prefill

Prefill speed

1 s

TTFT

Time to first token

7.77 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 · Q3_K_M Decode 80.3 · Prefill 259.75 ·
  2. Ollama · Q6_K Decode 49.41 · Prefill 234.65 ·
  3. Strata · Q5_K_S (current)Decode 92.36 · Prefill 496.83 ·

Core figures

Decode (avg)
92.36 tok/s
Prefill (avg)
496.83 tok/s
TTFT (avg)
1 s
VRAM (avg)
7.77 GB
MTP acceptance rate
0.48
TTFB
0.74 GB
Power draw
187.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
Q5_K_S
Framework
Strata
Version
v0.27
Context length
16384 tokens
Batch size
256
GPU layers
8
Flash Attention
Off

Hardware

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

GPU
Intel Arc 140V
Measured VRAM (avg)
7.77 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
187.5 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

    v0.27 · Ubuntu 24.04 · CUDA 12.6 · 16384 ctx

    92.36 tok/s

    Decode

    496.83 tok/s

    Prefill

    1 s

    TTFT

    7.77 GB

    VRAM

    0.48

    MTP

    187.5 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=98 running model_id=60 at Q5_K_S