Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q5_K_S

Start a discussion
NVIDIA DGX Spark128GBvLLM v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q5_K_S) on NVIDIA DGX Spark with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

364.71 tok/s

Decode

Decode speed

1,715.93 tok/s

Prefill

Prefill speed

1.71 s

TTFT

Time to first token

3.23 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 Decode 353.22 · Prefill 1765.39 ·
  2. vLLM · Q5_K_S (current)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)
364.71 tok/s
Prefill (avg)
1,715.93 tok/s
TTFT (avg)
1.71 s
VRAM (avg)
3.23 GB
MTP acceptance rate
—
TTFB
2.92 GB
Power draw
261.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q5_K_S
Framework
vLLM
Version
v0.47
Context length
8192 tokens
Batch size
32
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)
3.23 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.6
Power draw
261.5 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

    v0.47 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx

    364.71 tok/s

    Decode

    1,715.93 tok/s

    Prefill

    1.71 s

    TTFT

    3.23 GB

    VRAM

    —

    MTP

    261.5 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=54 running model_id=62 at Q5_K_S