Arao AI
Back to search results

gemma-4-12B-it · Q3_K_S

Start a discussion
Apple M5 Pro64GBOllama v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q3_K_S) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

111.33 tok/s

Decode

Decode speed

497.48 tok/s

Prefill

Prefill speed

0.35 s

TTFT

Time to first token

18.48 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 · Q4_K_M Decode 100.37 · Prefill 374.04 ·
  2. llama.cpp · Q8_0 Decode 66.87 · Prefill 301.78 ·
  3. Ollama · Q3_K_M Decode 110.36 · Prefill 569.49 ·
  4. Ollama · Q3_K_S (current)Decode 111.33 · Prefill 497.48 ·

Core figures

Decode (avg)
111.33 tok/s
Prefill (avg)
497.48 tok/s
TTFT (avg)
0.35 s
VRAM (avg)
18.48 GB
MTP acceptance rate
—
TTFB
0.89 GB
Power draw
44.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q3_K_S
Framework
Ollama
Version
v0.31
Context length
2048 tokens
Batch size
512
GPU layers
33
Flash Attention
Off

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)
18.48 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
44.4 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

    v0.31 · macOS 15.0 · CUDA N/A · 2048 ctx

    111.33 tok/s

    Decode

    497.48 tok/s

    Prefill

    0.35 s

    TTFT

    18.48 GB

    VRAM

    —

    MTP

    44.4 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=65 at Q3_K_S