Arao AI
Back to search results

Qwen3-4B · Q2_K

Start a discussion
Qualcomm Snapdragon 7 Gen 4Ollama v0.51L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (Q2_K) on Qualcomm Snapdragon 7 Gen 4 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

58.83 tok/s

Decode

Decode speed

269.66 tok/s

Prefill

Prefill speed

1.74 s

TTFT

Time to first token

6.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · Q2_K (current)Decode 58.83 · Prefill 269.66 ·
  2. Ollama · Q3_K_S Decode 51.27 · Prefill 253.88 ·

Core figures

Decode (avg)
58.83 tok/s
Prefill (avg)
269.66 tok/s
TTFT (avg)
1.74 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
0.47 GB
Power draw
27.3 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
Q2_K
Framework
Ollama
Version
v0.51
Context length
8192 tokens
Batch size
512
GPU layers
20
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)
6.72 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
27.3 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

    v0.51 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    58.83 tok/s

    Decode

    269.66 tok/s

    Prefill

    1.74 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    27.3 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=105 running model_id=54 at Q2_K