Arao AI
Back to search results

Qwen3-4B-Thinking-2507 · Q3_K_M

Start a discussion
Intel Arc 140VvLLM v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q3_K_M) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

77.55 tok/s

Decode

Decode speed

286.29 tok/s

Prefill

Prefill speed

1.1 s

TTFT

Time to first token

7.81 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 · Q3_K_M (current)Decode 77.55 · Prefill 286.29 ·
  2. Ollama · Q4_K_S Decode 56.88 · Prefill 225.68 ·

Core figures

Decode (avg)
77.55 tok/s
Prefill (avg)
286.29 tok/s
TTFT (avg)
1.1 s
VRAM (avg)
7.81 GB
MTP acceptance rate
—
TTFB
0.62 GB
Power draw
174.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B-Thinking-2507
Quantization
Q3_K_M
Framework
vLLM
Version
v0.39
Context length
16384 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

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)
7.81 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
174.3 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

    v0.39 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    77.55 tok/s

    Decode

    286.29 tok/s

    Prefill

    1.1 s

    TTFT

    7.81 GB

    VRAM

    —

    MTP

    174.3 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=57 at Q3_K_M