Arao AI
Back to search results

gemma-4-E4B-it · IQ3_S

Start a discussion
Apple M5 Ultra512GBllama.cpp v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_S) on Apple M5 Ultra with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

153.37 tok/s

Decode

Decode speed

580.58 tok/s

Prefill

Prefill speed

1.38 s

TTFT

Time to first token

13.19 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. llama.cpp · IQ3_S (current)Decode 153.37 · Prefill 580.58 ·
  2. Ollama · IQ2_M Decode 156.39 · Prefill 558.43 ·

Core figures

Decode (avg)
153.37 tok/s
Prefill (avg)
580.58 tok/s
TTFT (avg)
1.38 s
VRAM (avg)
13.19 GB
MTP acceptance rate
—
TTFB
1.23 GB
Power draw
121.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ3_S
Framework
llama.cpp
Version
v0.47
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
Apple M5 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
13.19 GB
OS
macOS 26.1
Power draw
121.7 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-24

    v0.47 · macOS 26.1 · 4096 ctx

    153.37 tok/s

    Decode

    580.58 tok/s

    Prefill

    1.38 s

    TTFT

    13.19 GB

    VRAM

    —

    MTP

    121.7 W

    Power draw

    L2 batch seed 2026-10-24: llama.cpp on hw_id=29 running model_id=67 at IQ3_S