Arao AI
Back to search results

gemma-4-E4B-it · Q4_K_S

Start a discussion
Qualcomm Snapdragon 7 Gen 4llama.cpp v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q4_K_S) on Qualcomm Snapdragon 7 Gen 4 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

45.34 tok/s

Decode

Decode speed

207.38 tok/s

Prefill

Prefill speed

1.84 s

TTFT

Time to first token

7.6 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 · Q4_K_S (current)Decode 45.34 · Prefill 207.38 ·
  2. Strata · IQ4_XS Decode 74.19 · Prefill 369.77 ·

Core figures

Decode (avg)
45.34 tok/s
Prefill (avg)
207.38 tok/s
TTFT (avg)
1.84 s
VRAM (avg)
7.6 GB
MTP acceptance rate
—
TTFB
0.36 GB
Power draw
31 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q4_K_S
Framework
llama.cpp
Version
v0.52
Context length
8192 tokens
Batch size
256
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)
7.6 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
31 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 · 8192 ctx

    45.34 tok/s

    Decode

    207.38 tok/s

    Prefill

    1.84 s

    TTFT

    7.6 GB

    VRAM

    —

    MTP

    31 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=105 running model_id=67 at Q4_K_S