Arao AI
Back to search results

Qwen3-4B · Q4_K_M

Start a discussion
Intel Arc 140VOllama v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q4_K_M) on Intel Arc 140V with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

54.47 tok/s

Decode

Decode speed

248.92 tok/s

Prefill

Prefill speed

1.38 s

TTFT

Time to first token

8.99 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ3_S Decode 80.06 · Prefill 290.03 ·
  2. vLLM · Q8_0 Decode 42.86 · Prefill 150.62 ·
  3. Ollama · IQ1_S Decode 81.27 · Prefill 262.71 ·
  4. Ollama · Q4_K_M (current)Decode 54.47 · Prefill 248.92 ·

Core figures

Decode (avg)
54.47 tok/s
Prefill (avg)
248.92 tok/s
TTFT (avg)
1.38 s
VRAM (avg)
8.99 GB
MTP acceptance rate
—
TTFB
0.44 GB
Power draw
169.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q4_K_M
Framework
Ollama
Version
v0.48
Context length
32768 tokens
Batch size
512
GPU layers
33
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)
8.99 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
169.4 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

    v0.48 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx

    54.47 tok/s

    Decode

    248.92 tok/s

    Prefill

    1.38 s

    TTFT

    8.99 GB

    VRAM

    —

    MTP

    169.4 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=98 running model_id=54 at Q4_K_M