Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · Q6_K

Start a discussion
Qualcomm Snapdragon 7 Gen 4Strata v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (Q6_K) on Qualcomm Snapdragon 7 Gen 4 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

115.51 tok/s

Decode

Decode speed

492.04 tok/s

Prefill

Prefill speed

2.22 s

TTFT

Time to first token

3.15 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 · IQ3_XS Decode 150.77 · Prefill 624.32 ·
  2. Strata · Q6_K (current)Decode 115.51 · Prefill 492.04 ·

Core figures

Decode (avg)
115.51 tok/s
Prefill (avg)
492.04 tok/s
TTFT (avg)
2.22 s
VRAM (avg)
3.15 GB
MTP acceptance rate
0.67
TTFB
0.92 GB
Power draw
34 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
Q6_K
Framework
Strata
Version
v0.40
Context length
32768 tokens
Batch size
512
GPU layers
12
Flash Attention
Off

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)
3.15 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
34 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

    v0.40 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    115.51 tok/s

    Decode

    492.04 tok/s

    Prefill

    2.22 s

    TTFT

    3.15 GB

    VRAM

    0.67

    MTP

    34 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=105 running model_id=59 at Q6_K