Arao AI
Back to search results

gemma-4-E4B-it · Q8_0

Start a discussion
Apple M1 MaxOllama v0.25L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q8_0) on Apple M1 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

65.55 tok/s

Decode

Decode speed

302.64 tok/s

Prefill

Prefill speed

2.3 s

TTFT

Time to first token

11.76 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 · Q8_0 (current)Decode 65.55 · Prefill 302.64 ·
  2. Strata · IQ2_M Decode 209.31 · Prefill 930.07 ·

Core figures

Decode (avg)
65.55 tok/s
Prefill (avg)
302.64 tok/s
TTFT (avg)
2.3 s
VRAM (avg)
11.76 GB
MTP acceptance rate
—
TTFB
0.52 GB
Power draw
40 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q8_0
Framework
Ollama
Version
v0.25
Context length
32768 tokens
Batch size
512
GPU layers
33
Flash Attention
On

Hardware

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

GPU
Apple M1 Max
Measured VRAM (avg)
11.76 GB
OS
macOS 15.0
Driver
Apple M1 Max
CUDA
N/A
Power draw
40 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 · macOS 15.0 · CUDA N/A · 32768 ctx

    65.55 tok/s

    Decode

    302.64 tok/s

    Prefill

    2.3 s

    TTFT

    11.76 GB

    VRAM

    —

    MTP

    40 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=101 running model_id=67 at Q8_0