Arao AI
Back to search results

Qwen3-Embedding-0.6B · Q6_K

Start a discussion
Qualcomm Snapdragon X EliteStrata v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q6_K) on Qualcomm Snapdragon X Elite with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

148.28 tok/s

Decode

Decode speed

791.63 tok/s

Prefill

Prefill speed

0.28 s

TTFT

Time to first token

3.36 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 · Q4_K_S Decode 152.62 · Prefill 807.12 ·
  2. Strata · Q6_K (current)Decode 148.28 · Prefill 791.63 ·

Core figures

Decode (avg)
148.28 tok/s
Prefill (avg)
791.63 tok/s
TTFT (avg)
0.28 s
VRAM (avg)
3.36 GB
MTP acceptance rate
0.65
TTFB
1.19 GB
Power draw
32.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-Embedding-0.6B
Quantization
Q6_K
Framework
Strata
Version
v0.52
Context length
4096 tokens
Batch size
256
GPU layers
15
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
Qualcomm Snapdragon X Elite
Measured VRAM (avg)
3.36 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
32.3 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

    v0.52 · Windows 11 23H2 · CUDA N/A · 4096 ctx

    148.28 tok/s

    Decode

    791.63 tok/s

    Prefill

    0.28 s

    TTFT

    3.36 GB

    VRAM

    0.65

    MTP

    32.3 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=104 running model_id=62 at Q6_K