Arao AI
Back to search results

gemma-4-E2B-it · Q3_K_L

Start a discussion
Qualcomm Snapdragon X EliteStrata v0.28L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q3_K_L) on Qualcomm Snapdragon X Elite with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

121.82 tok/s

Decode

Decode speed

519.2 tok/s

Prefill

Prefill speed

1.13 s

TTFT

Time to first token

5.12 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 · Q4_K_M Decode 76.52 · Prefill 395.44 ·
  2. Strata · Q2_K Decode 154.6 · Prefill 695.42 ·
  3. Strata · Q3_K_L (current)Decode 121.82 · Prefill 519.2 ·

Core figures

Decode (avg)
121.82 tok/s
Prefill (avg)
519.2 tok/s
TTFT (avg)
1.13 s
VRAM (avg)
5.12 GB
MTP acceptance rate
0.68
TTFB
0.97 GB
Power draw
9.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q3_K_L
Framework
Strata
Version
v0.28
Context length
32768 tokens
Batch size
512
GPU layers
8
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)
5.12 GB
OS
Windows 11 23H2
Driver
Qualcomm Adreno 7.0
CUDA
N/A
Power draw
9.8 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

    v0.28 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    121.82 tok/s

    Decode

    519.2 tok/s

    Prefill

    1.13 s

    TTFT

    5.12 GB

    VRAM

    0.68

    MTP

    9.8 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=104 running model_id=66 at Q3_K_L