Arao AI
Back to search results

gemma-4-E4B-it · FP16

Start a discussion
Apple M2 ProvLLM v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (FP16) on Apple M2 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

45.65 tok/s

Decode

Decode speed

229.99 tok/s

Prefill

Prefill speed

2.42 s

TTFT

Time to first token

17.64 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 · FP16 (current)Decode 45.65 · Prefill 229.99 ·
  2. vLLM · IQ3_S Decode 120.89 · Prefill 462.7 ·
  3. Ollama · Q3_K_S Decode 106.08 · Prefill 378.66 ·

Core figures

Decode (avg)
45.65 tok/s
Prefill (avg)
229.99 tok/s
TTFT (avg)
2.42 s
VRAM (avg)
17.64 GB
MTP acceptance rate
—
TTFB
0.37 GB
Power draw
59.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
FP16
Framework
vLLM
Version
v0.34
Context length
16384 tokens
Batch size
16
GPU layers
999
Flash Attention
Off

Hardware

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

GPU
Apple M2 Pro
Measured VRAM (avg)
17.64 GB
OS
macOS 15.0
Driver
Apple M2 Pro
CUDA
N/A
Power draw
59.5 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

    v0.34 · macOS 15.0 · CUDA N/A · 16384 ctx

    45.65 tok/s

    Decode

    229.99 tok/s

    Prefill

    2.42 s

    TTFT

    17.64 GB

    VRAM

    —

    MTP

    59.5 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=102 running model_id=67 at FP16