Arao AI
Back to search results

gemma-4-E2B-it · Q6_K

Start a discussion
Apple M1llama.cpp v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q6_K) on Apple M1 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

62.45 tok/s

Decode

Decode speed

267.16 tok/s

Prefill

Prefill speed

0.33 s

TTFT

Time to first token

6.3 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ2_XS Decode 125.44 · Prefill 495.34 ·
  2. llama.cpp · Q6_K (current)Decode 62.45 · Prefill 267.16 ·
  3. Ollama · IQ2_XS Decode 113.15 · Prefill 569.16 ·
  4. Ollama · IQ3_S Decode 89.33 · Prefill 357.04 ·

Core figures

Decode (avg)
62.45 tok/s
Prefill (avg)
267.16 tok/s
TTFT (avg)
0.33 s
VRAM (avg)
6.3 GB
MTP acceptance rate
—
TTFB
0.5 GB
Power draw
50.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q6_K
Framework
llama.cpp
Version
v0.24
Context length
8192 tokens
Batch size
512
GPU layers
20
Flash Attention
Off

Hardware

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

GPU
Apple M1
Measured VRAM (avg)
6.3 GB
OS
macOS 15.0
Driver
Apple M1
CUDA
N/A
Power draw
50.7 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

    v0.24 · macOS 15.0 · CUDA N/A · 8192 ctx

    62.45 tok/s

    Decode

    267.16 tok/s

    Prefill

    0.33 s

    TTFT

    6.3 GB

    VRAM

    —

    MTP

    50.7 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=99 running model_id=66 at Q6_K