Arao AI
Back to search results

gemma-4-31B-it · IQ1_S

Start a discussion
Apple M5 Max128GBllama.cpp v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ1_S) on Apple M5 Max with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

64.71 tok/s

Decode

Decode speed

267.16 tok/s

Prefill

Prefill speed

0.33 s

TTFT

Time to first token

29.44 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · IQ1_S (current)Decode 64.71 · Prefill 267.16 ·
  2. llama.cpp · IQ2_XS Decode 58.24 · Prefill 303.37 ·
  3. Ollama · Q4_K_M Decode 32.9 · Prefill 145.14 ·
  4. Strata · IQ4_XS Decode 138.4 · Prefill 718.68 ·
  5. Strata · Q3_K_M Decode 149.39 · Prefill 771.31 ·

Core figures

Decode (avg)
64.71 tok/s
Prefill (avg)
267.16 tok/s
TTFT (avg)
0.33 s
VRAM (avg)
29.44 GB
MTP acceptance rate
—
TTFB
0.52 GB
Power draw
48.9 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.41
Context length
32768 tokens
Batch size
256
GPU layers
33
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)
29.44 GB
OS
macOS 26.1
Power draw
48.9 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

    v0.41 · macOS 26.1 · 32768 ctx

    64.71 tok/s

    Decode

    267.16 tok/s

    Prefill

    0.33 s

    TTFT

    29.44 GB

    VRAM

    —

    MTP

    48.9 W

    Power draw

    L2 batch seed 2026-10-19: llama.cpp on hw_id=28 running model_id=63 at IQ1_S