Arao AI
Back to search results

gemma-4-31B-it · Q3_K_M

Start a discussion
Apple M5 Pro64GBOllama v0.43L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q3_K_M) on Apple M5 Pro with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

62.31 tok/s

Decode

Decode speed

340.97 tok/s

Prefill

Prefill speed

2.06 s

TTFT

Time to first token

46.37 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · Q3_K_M (current)Decode 62.31 · Prefill 340.97 ·
  2. Strata · IQ3_XS Decode 111.36 · Prefill 546.98 ·

Core figures

Decode (avg)
62.31 tok/s
Prefill (avg)
340.97 tok/s
TTFT (avg)
2.06 s
VRAM (avg)
46.37 GB
MTP acceptance rate
—
TTFB
0.5 GB
Power draw
101.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q3_K_M
Framework
Ollama
Version
v0.43
Context length
8192 tokens
Batch size
512
GPU layers
99
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)
46.37 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
101.2 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

    v0.43 · macOS 15.0 · CUDA N/A · 8192 ctx

    62.31 tok/s

    Decode

    340.97 tok/s

    Prefill

    2.06 s

    TTFT

    46.37 GB

    VRAM

    —

    MTP

    101.2 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=27 running model_id=63 at Q3_K_M