Arao AI
Back to search results

gemma-4-31B-it · IQ2_XS

Start a discussion
Apple M2 UltraOllama v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ2_XS) on Apple M2 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

73.22 tok/s

Decode

Decode speed

389.92 tok/s

Prefill

Prefill speed

1.45 s

TTFT

Time to first token

33.35 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. llama.cpp · Q4_K_M Decode 58.99 · Prefill 259.24 ·
  2. Ollama · IQ2_XS (current)Decode 73.22 · Prefill 389.92 ·

Core figures

Decode (avg)
73.22 tok/s
Prefill (avg)
389.92 tok/s
TTFT (avg)
1.45 s
VRAM (avg)
33.35 GB
MTP acceptance rate
—
TTFB
0.59 GB
Power draw
103.3 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ2_XS
Framework
Ollama
Version
v0.37
Context length
2048 tokens
Batch size
512
GPU layers
28
Flash Attention
On

Hardware

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

GPU
Apple M2 Ultra
Measured VRAM (avg)
33.35 GB
OS
macOS 26.1
Power draw
103.3 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.37 · macOS 26.1 · 2048 ctx

    73.22 tok/s

    Decode

    389.92 tok/s

    Prefill

    1.45 s

    TTFT

    33.35 GB

    VRAM

    —

    MTP

    103.3 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=103 running model_id=63 at IQ2_XS