Arao AI
Back to search results

gemma-4-E2B-it · Q3_K_L

Start a discussion
Apple M5 Max128GBStrata v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q3_K_L) on Apple M5 Max with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

329.61 tok/s

Decode

Decode speed

1,762.01 tok/s

Prefill

Prefill speed

0.67 s

TTFT

Time to first token

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

Core figures

Decode (avg)
329.61 tok/s
Prefill (avg)
1,762.01 tok/s
TTFT (avg)
0.67 s
VRAM (avg)
5.12 GB
MTP acceptance rate
0.73
TTFB
2.64 GB
Power draw
255.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q3_K_L
Framework
Strata
Version
v0.37
Context length
2048 tokens
Batch size
1024
GPU layers
5
Flash Attention
Off

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)
5.12 GB
OS
Ubuntu 22.04
Driver
565.57
CUDA
12.8
Power draw
255.8 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

    v0.37 · Ubuntu 22.04 · CUDA 12.8 · 2048 ctx

    329.61 tok/s

    Decode

    1,762.01 tok/s

    Prefill

    0.67 s

    TTFT

    5.12 GB

    VRAM

    0.73

    MTP

    255.8 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=28 running model_id=66 at Q3_K_L