Arao AI
Back to search results

Qwen3-1.7B · IQ2_M

Start a discussion
Intel Arc 140VOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (IQ2_M) on Intel Arc 140V with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

112.05 tok/s

Decode

Decode speed

542.45 tok/s

Prefill

Prefill speed

1.75 s

TTFT

Time to first token

3.96 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 · IQ2_M (current)Decode 112.05 · Prefill 542.45 ·
  2. Ollama · Q5_K_S Decode 71.63 · Prefill 287.36 ·
  3. Strata · Q4_K_S Decode 123.42 · Prefill 651.16 ·
  4. Strata · Q5_K_S Decode 111.13 · Prefill 553 ·

Core figures

Decode (avg)
112.05 tok/s
Prefill (avg)
542.45 tok/s
TTFT (avg)
1.75 s
VRAM (avg)
3.96 GB
MTP acceptance rate
—
TTFB
0.9 GB
Power draw
218.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
IQ2_M
Framework
Ollama
Version
v0.25
Context length
4096 tokens
Batch size
512
GPU layers
20
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)
3.96 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
218.5 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

    v0.25 · Windows 11 23H2 · CUDA 12.6 · 4096 ctx

    112.05 tok/s

    Decode

    542.45 tok/s

    Prefill

    1.75 s

    TTFT

    3.96 GB

    VRAM

    —

    MTP

    218.5 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=98 running model_id=55 at IQ2_M