Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ2_XS

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_XS) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

245.41 tok/s

Decode

Decode speed

864.37 tok/s

Prefill

Prefill speed

1.25 s

TTFT

Time to first token

2.71 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S Decode 232.92 · Prefill 851.04 ·
  2. llama.cpp · Q5_K_S Decode 140.38 · Prefill 456.07 ·
  3. Ollama · Q5_K_S Decode 120.47 · Prefill 591.73 ·
  4. vLLM · IQ2_XS (current)Decode 245.41 · Prefill 864.37 ·

Core figures

Decode (avg)
245.41 tok/s
Prefill (avg)
864.37 tok/s
TTFT (avg)
1.25 s
VRAM (avg)
2.71 GB
MTP acceptance rate
—
TTFB
1.96 GB
Power draw
25.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ2_XS
Framework
vLLM
Version
v0.20
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
NVIDIA Jetson AGX Orin 64GB
Nominal VRAM
64 GB
Measured VRAM (avg)
2.71 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
25.8 W

Sources & evidence

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

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

    v0.20 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    245.41 tok/s

    Decode

    864.37 tok/s

    Prefill

    1.25 s

    TTFT

    2.71 GB

    VRAM

    —

    MTP

    25.8 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=76 running model_id=62 at IQ2_XS