Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ1_S

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBllama.cpp v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ1_S) on NVIDIA Jetson AGX Orin 64GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

232.92 tok/s

Decode

Decode speed

851.04 tok/s

Prefill

Prefill speed

1.8 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. llama.cpp · IQ1_S (current)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 Decode 245.41 · Prefill 864.37 ·

Core figures

Decode (avg)
232.92 tok/s
Prefill (avg)
851.04 tok/s
TTFT (avg)
1.8 s
VRAM (avg)
2.62 GB
MTP acceptance rate
—
TTFB
1.86 GB
Power draw
28.7 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.45
Context length
8192 tokens
Batch size
256
GPU layers
33
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)
2.62 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
28.7 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 · JetPack 6.0 · CUDA 12.6 · 8192 ctx

    232.92 tok/s

    Decode

    851.04 tok/s

    Prefill

    1.8 s

    TTFT

    2.62 GB

    VRAM

    —

    MTP

    28.7 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=76 running model_id=62 at IQ1_S