Arao AI
Back to search results

gemma-4-26B-A4B-it · Q8_0

Start a discussion
Apple M5 Pro64GBllama.cpp v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (Q8_0) on Apple M5 Pro with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

55.26 tok/s

Decode

Decode speed

261.28 tok/s

Prefill

Prefill speed

1.58 s

TTFT

Time to first token

60.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. llama.cpp · Q8_0 (current)Decode 55.26 · Prefill 261.28 ·
  2. Strata · Q6_K Decode 98.9 · Prefill 379.8 ·

Core figures

Decode (avg)
55.26 tok/s
Prefill (avg)
261.28 tok/s
TTFT (avg)
1.58 s
VRAM (avg)
60.8 GB
MTP acceptance rate
—
TTFB
0.44 GB
Power draw
58.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-26B-A4B-it
Quantization
Q8_0
Framework
llama.cpp
Version
v0.37
Context length
2048 tokens
Batch size
256
GPU layers
99
Flash Attention
On

Hardware

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

GPU
Apple M5 Pro
Nominal VRAM
64 GB
Measured VRAM (avg)
60.8 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
58.1 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.37 · macOS 15.0 · CUDA N/A · 2048 ctx

    55.26 tok/s

    Decode

    261.28 tok/s

    Prefill

    1.58 s

    TTFT

    60.8 GB

    VRAM

    —

    MTP

    58.1 W

    Power draw

    L2 batch seed 2026-10-13: llama.cpp on hw_id=27 running model_id=64 at Q8_0