Arao AI
Back to search results

gemma-4-31B-it · IQ3_XS

Start a discussion
Apple M5 Pro64GBStrata v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ3_XS) on Apple M5 Pro with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

111.36 tok/s

Decode

Decode speed

546.98 tok/s

Prefill

Prefill speed

2.41 s

TTFT

Time to first token

42.46 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 Decode 62.31 · Prefill 340.97 ·
  2. Strata · IQ3_XS (current)Decode 111.36 · Prefill 546.98 ·

Core figures

Decode (avg)
111.36 tok/s
Prefill (avg)
546.98 tok/s
TTFT (avg)
2.41 s
VRAM (avg)
42.46 GB
MTP acceptance rate
0.58
TTFB
0.89 GB
Power draw
43.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ3_XS
Framework
Strata
Version
v0.41
Context length
4096 tokens
Batch size
512
GPU layers
12
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)
42.46 GB
OS
macOS 15.0
Driver
Apple M5 Pro
CUDA
N/A
Power draw
43.6 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

    v0.41 · macOS 15.0 · CUDA N/A · 4096 ctx

    111.36 tok/s

    Decode

    546.98 tok/s

    Prefill

    2.41 s

    TTFT

    42.46 GB

    VRAM

    0.58

    MTP

    43.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=27 running model_id=63 at IQ3_XS