Arao AI
Back to search results

gemma-4-E4B-it · Q2_K

Start a discussion
Apple M5 Max128GBOllama v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q2_K) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

303.01 tok/s

Decode

Decode speed

1,437.6 tok/s

Prefill

Prefill speed

1.76 s

TTFT

Time to first token

6.72 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 Decode 264.68 · Prefill 1192.68 ·
  2. Ollama · Q2_K (current)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)
303.01 tok/s
Prefill (avg)
1,437.6 tok/s
TTFT (avg)
1.76 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
2.42 GB
Power draw
231.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q2_K
Framework
Ollama
Version
v0.41
Context length
8192 tokens
Batch size
256
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 M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
6.72 GB
OS
Ubuntu 24.04
Driver
555.85
CUDA
12.4
Power draw
231.8 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

    v0.41 · Ubuntu 24.04 · CUDA 12.4 · 8192 ctx

    303.01 tok/s

    Decode

    1,437.6 tok/s

    Prefill

    1.76 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    231.8 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=28 running model_id=67 at Q2_K