Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ2_M

Start a discussion
Intel Arc 140VvLLM v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_M) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

187.46 tok/s

Decode

Decode speed

728.79 tok/s

Prefill

Prefill speed

0.45 s

TTFT

Time to first token

2.75 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 · IQ2_M (current)Decode 187.46 · Prefill 728.79 ·
  2. vLLM · IQ3_S Decode 169.96 · Prefill 565.7 ·
  3. Ollama · IQ3_S Decode 157.23 · Prefill 521.64 ·

Core figures

Decode (avg)
187.46 tok/s
Prefill (avg)
728.79 tok/s
TTFT (avg)
0.45 s
VRAM (avg)
2.75 GB
MTP acceptance rate
—
TTFB
1.5 GB
Power draw
168 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ2_M
Framework
vLLM
Version
v0.41
Context length
8192 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)
2.75 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
168 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

    v0.41 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    187.46 tok/s

    Decode

    728.79 tok/s

    Prefill

    0.45 s

    TTFT

    2.75 GB

    VRAM

    —

    MTP

    168 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=62 at IQ2_M