Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ1_S

Start a discussion
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ1_S) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

337.12 tok/s

Decode

Decode speed

1,106.41 tok/s

Prefill

Prefill speed

0.75 s

TTFT

Time to first token

2.54 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 · IQ1_S (current)Decode 337.12 · Prefill 1106.41 ·

Core figures

Decode (avg)
337.12 tok/s
Prefill (avg)
1,106.41 tok/s
TTFT (avg)
0.75 s
VRAM (avg)
2.54 GB
MTP acceptance rate
—
TTFB
2.7 GB
Power draw
270.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.43
Context length
32768 tokens
Batch size
256
GPU layers
33
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)
2.54 GB
OS
macOS 15.0
Driver
570.86
CUDA
12.4
Power draw
270.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.43 · macOS 15.0 · CUDA 12.4 · 32768 ctx

    337.12 tok/s

    Decode

    1,106.41 tok/s

    Prefill

    0.75 s

    TTFT

    2.54 GB

    VRAM

    —

    MTP

    270.5 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=3 running model_id=59 at IQ1_S