Arao AI
Back to search results

gemma-4-E4B-it · Q4_K_S

Start a discussion
Apple M1 ProOllama v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q4_K_S) on Apple M1 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

77.92 tok/s

Decode

Decode speed

280.34 tok/s

Prefill

Prefill speed

2.08 s

TTFT

Time to first token

8.65 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · Q2_K Decode 122.43 · Prefill 598.25 ·
  2. vLLM · Q3_K_M Decode 98.62 · Prefill 525.36 ·
  3. Ollama · Q4_K_S (current)Decode 77.92 · Prefill 280.34 ·

Core figures

Decode (avg)
77.92 tok/s
Prefill (avg)
280.34 tok/s
TTFT (avg)
2.08 s
VRAM (avg)
8.65 GB
MTP acceptance rate
—
TTFB
0.62 GB
Power draw
41.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q4_K_S
Framework
Ollama
Version
v0.52
Context length
8192 tokens
Batch size
512
GPU layers
99
Flash Attention
On

Hardware

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

GPU
Apple M1 Pro
Measured VRAM (avg)
8.65 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
41.5 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

    v0.52 · macOS 15.0 · CUDA N/A · 8192 ctx

    77.92 tok/s

    Decode

    280.34 tok/s

    Prefill

    2.08 s

    TTFT

    8.65 GB

    VRAM

    —

    MTP

    41.5 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=100 running model_id=67 at Q4_K_S