Arao AI
Back to search results

gemma-4-12B-it · IQ2_M

Start a discussion
Apple M5 Max128GBOllama v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

66.82 tok/s

Decode

Decode speed

219.12 tok/s

Prefill

Prefill speed

2.3 s

TTFT

Time to first token

15.2 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 · IQ3_S Decode 67.49 · Prefill 263.38 ·
  2. Ollama · IQ2_M (current)Decode 66.82 · Prefill 219.12 ·
  3. Ollama · Q5_K_M Decode 43.37 · Prefill 143.55 ·
  4. Strata · Q4_K_S Decode 224.6 · Prefill 779.88 ·

Core figures

Decode (avg)
66.82 tok/s
Prefill (avg)
219.12 tok/s
TTFT (avg)
2.3 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.53 GB
Power draw
42.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_M
Framework
Ollama
Version
v0.24
Context length
2048 tokens
Batch size
512
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 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
15.2 GB
OS
macOS 26.1
Power draw
42.7 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

    v0.24 · macOS 26.1 · 2048 ctx

    66.82 tok/s

    Decode

    219.12 tok/s

    Prefill

    2.3 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    42.7 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=65 at IQ2_M