Arao AI
Back to search results

Qwen3-Embedding-0.6B · IQ2_XS

Start a discussion
Qualcomm Snapdragon 7 Gen 4llama.cpp v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_XS) on Qualcomm Snapdragon 7 Gen 4 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

156.09 tok/s

Decode

Decode speed

630.03 tok/s

Prefill

Prefill speed

1.73 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

2 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS (current)Decode 156.09 · Prefill 630.03 ·
  2. Strata · Q3_K_M Decode 155.2 · Prefill 688.84 ·
  3. Strata · Q5_K_S Decode 117.77 · Prefill 410.82 ·

Core figures

Decode (avg)
156.09 tok/s
Prefill (avg)
630.03 tok/s
TTFT (avg)
1.73 s
VRAM (avg)
2.71 GB
MTP acceptance rate
—
TTFB
1.25 GB
Power draw
18.8 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
IQ2_XS
Framework
llama.cpp
Version
v0.46
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
Qualcomm Snapdragon 7 Gen 4
Measured VRAM (avg)
2.71 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
18.8 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

    v0.46 · Windows 11 23H2 · CUDA N/A · 4096 ctx

    156.09 tok/s

    Decode

    630.03 tok/s

    Prefill

    1.73 s

    TTFT

    2.71 GB

    VRAM

    —

    MTP

    18.8 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=105 running model_id=62 at IQ2_XS