Arao AI
Back to search results

Qwen3-4B · IQ3_S

Start a discussion
Intel Arc 140VvLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ3_S) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

80.06 tok/s

Decode

Decode speed

290.03 tok/s

Prefill

Prefill speed

1.58 s

TTFT

Time to first token

7.64 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 (current)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 Decode 54.47 · Prefill 248.92 ·

Core figures

Decode (avg)
80.06 tok/s
Prefill (avg)
290.03 tok/s
TTFT (avg)
1.58 s
VRAM (avg)
7.64 GB
MTP acceptance rate
—
TTFB
0.64 GB
Power draw
183.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ3_S
Framework
vLLM
Version
v0.22
Context length
4096 tokens
Batch size
16
GPU layers
999
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)
7.64 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
183.5 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

    v0.22 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    80.06 tok/s

    Decode

    290.03 tok/s

    Prefill

    1.58 s

    TTFT

    7.64 GB

    VRAM

    —

    MTP

    183.5 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=54 at IQ3_S