Arao AI
Back to search results

Qwen2.5-Omni-3B · Q2_K

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q2_K) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

164.89 tok/s

Decode

Decode speed

695.02 tok/s

Prefill

Prefill speed

1.02 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 · Q2_K (current)Decode 164.89 · Prefill 695.02 ·

Core figures

Decode (avg)
164.89 tok/s
Prefill (avg)
695.02 tok/s
TTFT (avg)
1.02 s
VRAM (avg)
5.57 GB
MTP acceptance rate
—
TTFB
1.32 GB
Power draw
361 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-Omni-3B
Quantization
Q2_K
Framework
llama.cpp
Version
v0.25
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX 4060 Ti 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
5.57 GB
OS
Windows 11 23H2
Driver
555.85
CUDA
12.8
Power draw
361 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

    v0.25 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx

    164.89 tok/s

    Decode

    695.02 tok/s

    Prefill

    1.02 s

    TTFT

    5.57 GB

    VRAM

    —

    MTP

    361 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=3 running model_id=60 at Q2_K