Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q4_K_M

Start a discussion
NVIDIA DGX Spark128GBOllama v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q4_K_M) on NVIDIA DGX Spark with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

393.8 tok/s

Decode

Decode speed

1,419.14 tok/s

Prefill

Prefill speed

0.13 s

TTFT

Time to first token

3.13 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ1_S 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 (current)Decode 393.8 · Prefill 1419.14 ·

Core figures

Decode (avg)
393.8 tok/s
Prefill (avg)
1,419.14 tok/s
TTFT (avg)
0.13 s
VRAM (avg)
3.13 GB
MTP acceptance rate
—
TTFB
3.15 GB
Power draw
231.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q4_K_M
Framework
Ollama
Version
v0.43
Context length
4096 tokens
Batch size
512
GPU layers
28
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)
3.13 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.8
Power draw
231.2 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.43 · Ubuntu 24.04 · CUDA 12.8 · 4096 ctx

    393.8 tok/s

    Decode

    1,419.14 tok/s

    Prefill

    0.13 s

    TTFT

    3.13 GB

    VRAM

    —

    MTP

    231.2 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=54 running model_id=62 at Q4_K_M