Arao AI
Back to search results

gemma-4-E4B-it · Q2_K

Start a discussion
Apple M1 ProvLLM v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q2_K) on Apple M1 Pro with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

122.43 tok/s

Decode

Decode speed

598.25 tok/s

Prefill

Prefill speed

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

Core figures

Decode (avg)
122.43 tok/s
Prefill (avg)
598.25 tok/s
TTFT (avg)
0.49 s
VRAM (avg)
6.72 GB
MTP acceptance rate
—
TTFB
0.98 GB
Power draw
54.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q2_K
Framework
vLLM
Version
v0.43
Context length
2048 tokens
Batch size
32
GPU layers
999
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)
6.72 GB
OS
macOS 15.0
Driver
Apple M1 Pro
CUDA
N/A
Power draw
54.5 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

    v0.43 · macOS 15.0 · CUDA N/A · 2048 ctx

    122.43 tok/s

    Decode

    598.25 tok/s

    Prefill

    0.49 s

    TTFT

    6.72 GB

    VRAM

    —

    MTP

    54.5 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=100 running model_id=67 at Q2_K