Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ1_S

Start a discussion
Intel Arc 140VOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ1_S) on Intel Arc 140V with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

197.42 tok/s

Decode

Decode speed

954.57 tok/s

Prefill

Prefill speed

0.86 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

2 days ago

Last verified

Performance

  1. Ollama · IQ1_S (current)Decode 197.42 · Prefill 954.57 ·
  2. Ollama · Q3_K_L Decode 140.91 · Prefill 564.18 ·
  3. Strata · Q2_K Decode 267.39 · Prefill 900.92 ·
  4. Strata · Q6_K Decode 163.25 · Prefill 570.35 ·

Core figures

Decode (avg)
197.42 tok/s
Prefill (avg)
954.57 tok/s
TTFT (avg)
0.86 s
VRAM (avg)
2.54 GB
MTP acceptance rate
—
TTFB
1.58 GB
Power draw
166.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ1_S
Framework
Ollama
Version
v0.44
Context length
4096 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
Intel Arc 140V
Measured VRAM (avg)
2.54 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
166.1 W

Sources & evidence

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

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

    v0.44 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    197.42 tok/s

    Decode

    954.57 tok/s

    Prefill

    0.86 s

    TTFT

    2.54 GB

    VRAM

    —

    MTP

    166.1 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=98 running model_id=59 at IQ1_S