Arao AI
Back to search results

Qwen3.5-4B · Q5_K_S

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

This page aggregates 1 real-world runs of Qwen3.5-4B (Q5_K_S) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

56.56 tok/s

Decode

Decode speed

269.34 tok/s

Prefill

Prefill speed

0.37 s

TTFT

Time to first token

9.66 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 86.1 · Prefill 275.57 ·
  2. llama.cpp · Q4_K_S Decode 66.95 · Prefill 214.51 ·
  3. vLLM · Q5_K_S (current)Decode 56.56 · Prefill 269.34 ·

Core figures

Decode (avg)
56.56 tok/s
Prefill (avg)
269.34 tok/s
TTFT (avg)
0.37 s
VRAM (avg)
9.66 GB
MTP acceptance rate
—
TTFB
0.45 GB
Power draw
213.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q5_K_S
Framework
vLLM
Version
v0.48
Context length
2048 tokens
Batch size
8
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)
9.66 GB
OS
Windows 11 23H2
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
213.8 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 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx

    56.56 tok/s

    Decode

    269.34 tok/s

    Prefill

    0.37 s

    TTFT

    9.66 GB

    VRAM

    —

    MTP

    213.8 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=48 at Q5_K_S