Arao AI
Back to search results

Qwen3-Coder-Next · IQ4_XS

Start a discussion
Intel Arc 140VvLLM v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ4_XS) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

47.85 tok/s

Decode

Decode speed

251.28 tok/s

Prefill

Prefill speed

1.9 s

TTFT

Time to first token

1.05 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 · IQ4_XS (current)Decode 47.85 · Prefill 251.28 ·
  2. Ollama · IQ4_XS Decode 45.29 · Prefill 217.37 ·
  3. Ollama · Q4_K_S Decode 43.87 · Prefill 209.43 ·

Core figures

Decode (avg)
47.85 tok/s
Prefill (avg)
251.28 tok/s
TTFT (avg)
1.9 s
VRAM (avg)
1.05 GB
MTP acceptance rate
—
TTFB
0.38 GB
Power draw
210.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Coder-Next
Quantization
IQ4_XS
Framework
vLLM
Version
v0.26
Context length
4096 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)
1.05 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
210.9 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

    v0.26 · Ubuntu 24.04 · CUDA 12.6 · 4096 ctx

    47.85 tok/s

    Decode

    251.28 tok/s

    Prefill

    1.9 s

    TTFT

    1.05 GB

    VRAM

    —

    MTP

    210.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=58 at IQ4_XS