Arao AI
Back to search results

gemma-4-12B-it · IQ2_M

Start a discussion
Apple M4 Max128GBllama.cpp v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on Apple M4 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

187.13 tok/s

Decode

Decode speed

653.55 tok/s

Prefill

Prefill speed

2.5 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

Today

Last verified

Performance

  1. llama.cpp · IQ2_M (current)Decode 187.13 · Prefill 653.55 ·
  2. llama.cpp · Q4_K_M Decode 140.93 · Prefill 615.86 ·
  3. vLLM · IQ3_XS Decode 181.71 · Prefill 766.49 ·
  4. Strata · Q2_K Decode 270.81 · Prefill 1355.35 ·

Core figures

Decode (avg)
187.13 tok/s
Prefill (avg)
653.55 tok/s
TTFT (avg)
2.5 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
1.5 GB
Power draw
69.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_M
Framework
llama.cpp
Version
v0.52
Context length
32768 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 M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
15.2 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
69.1 W

Sources & evidence

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

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

    v0.52 · macOS 15.0 · CUDA N/A · 32768 ctx

    187.13 tok/s

    Decode

    653.55 tok/s

    Prefill

    2.5 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    69.1 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=26 running model_id=65 at IQ2_M