Arao AI
Back to search results

gemma-4-E4B-it · IQ3_XS

Start a discussion
Apple M5 Max128GBOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_XS) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

264.68 tok/s

Decode

Decode speed

1,192.68 tok/s

Prefill

Prefill speed

1.24 s

TTFT

Time to first token

7.31 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 · IQ3_XS (current)Decode 264.68 · Prefill 1192.68 ·
  2. Ollama · Q2_K Decode 303.01 · Prefill 1437.6 ·
  3. Strata · FP16 Decode 155.09 · Prefill 679.29 ·
  4. Strata · Q3_K_L Decode 374.77 · Prefill 1948.71 ·

Core figures

Decode (avg)
264.68 tok/s
Prefill (avg)
1,192.68 tok/s
TTFT (avg)
1.24 s
VRAM (avg)
7.31 GB
MTP acceptance rate
—
TTFB
2.12 GB
Power draw
246.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ3_XS
Framework
Ollama
Version
v0.25
Context length
8192 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 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
7.31 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.6
Power draw
246.4 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

    v0.25 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    264.68 tok/s

    Decode

    1,192.68 tok/s

    Prefill

    1.24 s

    TTFT

    7.31 GB

    VRAM

    —

    MTP

    246.4 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=28 running model_id=67 at IQ3_XS