Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q4_K_S

Start a discussion
Intel Arc A770 16GB16GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q4_K_S) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

160.53 tok/s

Decode

Decode speed

840.14 tok/s

Prefill

Prefill speed

0.15 s

TTFT

Time to first token

3.09 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 · Q4_K_S (current)Decode 160.53 · Prefill 840.14 ·
  2. Ollama · IQ4_XS Decode 153.38 · Prefill 732.92 ·
  3. Ollama · Q5_K_M Decode 116.05 · Prefill 477.94 ·
  4. Ollama · Q5_K_S Decode 121.2 · Prefill 454.65 ·

Core figures

Decode (avg)
160.53 tok/s
Prefill (avg)
840.14 tok/s
TTFT (avg)
0.15 s
VRAM (avg)
3.09 GB
MTP acceptance rate
—
TTFB
1.28 GB
Power draw
158.1 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q4_K_S
Framework
vLLM
Version
v0.37
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 A770 16GB
Nominal VRAM
16 GB
Measured VRAM (avg)
3.09 GB
OS
Ubuntu 24.04
Driver
Intel Arc 31.0.101.5186
CUDA
12.6
Power draw
158.1 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

    v0.37 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx

    160.53 tok/s

    Decode

    840.14 tok/s

    Prefill

    0.15 s

    TTFT

    3.09 GB

    VRAM

    —

    MTP

    158.1 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=62 at Q4_K_S