Arao AI
Back to search results

gemma-4-31B-it · Q2_K

Start a discussion
Apple M5 Ultra512GBOllama v0.42L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q2_K) on Apple M5 Ultra with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

75.92 tok/s

Decode

Decode speed

280.65 tok/s

Prefill

Prefill speed

1.29 s

TTFT

Time to first token

37.91 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 · Q3_K_L Decode 65.89 · Prefill 258.39 ·
  2. llama.cpp · Q8_0 Decode 37.99 · Prefill 165.65 ·
  3. Ollama · Q2_K (current)Decode 75.92 · Prefill 280.65 ·
  4. Ollama · Q8_0 Decode 38.85 · Prefill 140.28 ·

Core figures

Decode (avg)
75.92 tok/s
Prefill (avg)
280.65 tok/s
TTFT (avg)
1.29 s
VRAM (avg)
37.91 GB
MTP acceptance rate
—
TTFB
0.61 GB
Power draw
121.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q2_K
Framework
Ollama
Version
v0.42
Context length
16384 tokens
Batch size
512
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 Ultra
Nominal VRAM
512 GB
Measured VRAM (avg)
37.91 GB
OS
macOS 26.1
Power draw
121.5 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

    v0.42 · macOS 26.1 · 16384 ctx

    75.92 tok/s

    Decode

    280.65 tok/s

    Prefill

    1.29 s

    TTFT

    37.91 GB

    VRAM

    —

    MTP

    121.5 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=29 running model_id=63 at Q2_K