Arao AI
Back to search results

gemma-4-31B-it · Q4_K_M

Start a discussion
Apple M5 Max128GBOllama v0.20L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q4_K_M) on Apple M5 Max with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

32.9 tok/s

Decode

Decode speed

145.14 tok/s

Prefill

Prefill speed

1.6 s

TTFT

Time to first token

55.48 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 Decode 64.71 · Prefill 267.16 ·
  2. llama.cpp · IQ2_XS Decode 58.24 · Prefill 303.37 ·
  3. Ollama · Q4_K_M (current)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)
32.9 tok/s
Prefill (avg)
145.14 tok/s
TTFT (avg)
1.6 s
VRAM (avg)
55.48 GB
MTP acceptance rate
—
TTFB
0.26 GB
Power draw
63.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q4_K_M
Framework
Ollama
Version
v0.20
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
Off

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)
55.48 GB
OS
macOS 26.1
Power draw
63.7 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

    v0.20 · macOS 26.1 · 4096 ctx

    32.9 tok/s

    Decode

    145.14 tok/s

    Prefill

    1.6 s

    TTFT

    55.48 GB

    VRAM

    —

    MTP

    63.7 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=28 running model_id=63 at Q4_K_M