Arao AI
Back to search results

gemma-4-E2B-it · Q3_K_M

Start a discussion
Apple M5 Max128GBvLLM v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q3_K_M) on Apple M5 Max with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

285.33 tok/s

Decode

Decode speed

927.76 tok/s

Prefill

Prefill speed

0.72 s

TTFT

Time to first token

4.96 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 · Q3_K_M (current)Decode 285.33 · Prefill 927.76 ·
  2. Strata · Q3_K_L Decode 329.61 · Prefill 1762.01 ·
  3. Strata · Q8_0 Decode 323.09 · Prefill 1252.89 ·

Core figures

Decode (avg)
285.33 tok/s
Prefill (avg)
927.76 tok/s
TTFT (avg)
0.72 s
VRAM (avg)
4.96 GB
MTP acceptance rate
—
TTFB
2.28 GB
Power draw
223.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q3_K_M
Framework
vLLM
Version
v0.54
Context length
16384 tokens
Batch size
8
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 M5 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
4.96 GB
OS
Windows 11 23H2
Driver
555.85
CUDA
12.6
Power draw
223.1 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

    v0.54 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx

    285.33 tok/s

    Decode

    927.76 tok/s

    Prefill

    0.72 s

    TTFT

    4.96 GB

    VRAM

    —

    MTP

    223.1 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=28 running model_id=66 at Q3_K_M