Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ1_S

Start a discussion
NVIDIA DGX Spark128GBvLLM v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ1_S) on NVIDIA DGX Spark with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

353.22 tok/s

Decode

Decode speed

1,765.39 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

2.62 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 · IQ1_S (current)Decode 353.22 · Prefill 1765.39 ·
  2. vLLM · Q5_K_S Decode 364.71 · Prefill 1715.93 ·
  3. Ollama · IQ2_M Decode 338.92 · Prefill 1553.22 ·
  4. Ollama · Q4_K_M Decode 393.8 · Prefill 1419.14 ·

Core figures

Decode (avg)
353.22 tok/s
Prefill (avg)
1,765.39 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
2.62 GB
MTP acceptance rate
—
TTFB
2.83 GB
Power draw
152.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ1_S
Framework
vLLM
Version
v0.45
Context length
2048 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
NVIDIA DGX Spark
Nominal VRAM
128 GB
Measured VRAM (avg)
2.62 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
152.8 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

    v0.45 · Windows 11 23H2 · CUDA 12.8 · 2048 ctx

    353.22 tok/s

    Decode

    1,765.39 tok/s

    Prefill

    0.67 s

    TTFT

    2.62 GB

    VRAM

    —

    MTP

    152.8 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=54 running model_id=62 at IQ1_S