Arao AI
Back to search results

gemma-4-12B-it · Q4_K_M

Start a discussion
Apple M4 Max128GBllama.cpp v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q4_K_M) on Apple M4 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

140.93 tok/s

Decode

Decode speed

615.86 tok/s

Prefill

Prefill speed

1.74 s

TTFT

Time to first token

22.76 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 Decode 187.13 · Prefill 653.55 ·
  2. llama.cpp · Q4_K_M (current)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)
140.93 tok/s
Prefill (avg)
615.86 tok/s
TTFT (avg)
1.74 s
VRAM (avg)
22.76 GB
MTP acceptance rate
—
TTFB
1.13 GB
Power draw
40.3 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q4_K_M
Framework
llama.cpp
Version
v0.29
Context length
32768 tokens
Batch size
256
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 M4 Max
Nominal VRAM
128 GB
Measured VRAM (avg)
22.76 GB
OS
macOS 15.0
Driver
Apple M4 Max
CUDA
N/A
Power draw
40.3 W

Sources & evidence

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

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

    v0.29 · macOS 15.0 · CUDA N/A · 32768 ctx

    140.93 tok/s

    Decode

    615.86 tok/s

    Prefill

    1.74 s

    TTFT

    22.76 GB

    VRAM

    —

    MTP

    40.3 W

    Power draw

    L2 batch seed 2026-10-10: llama.cpp on hw_id=26 running model_id=65 at Q4_K_M