Arao AI
Back to search results

gemma-4-12B-it · Q4_K_M

Start a discussion
AMD Ryzen AI Max+ 395128GBOllama v0.38L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q4_K_M) on AMD Ryzen AI Max+ 395 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

66.99 tok/s

Decode

Decode speed

227.06 tok/s

Prefill

Prefill speed

0.19 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

5 days ago

Last verified

Performance

  1. Ollama · Q4_K_M (current)Decode 66.99 · Prefill 227.06 ·
  2. Strata · Q8_0 Decode 71.19 · Prefill 287.95 ·

Core figures

Decode (avg)
66.99 tok/s
Prefill (avg)
227.06 tok/s
TTFT (avg)
0.19 s
VRAM (avg)
22.76 GB
MTP acceptance rate
—
TTFB
0.54 GB
Power draw
105.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q4_K_M
Framework
Ollama
Version
v0.38
Context length
16384 tokens
Batch size
512
GPU layers
28
Flash Attention
Off

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
AMD Ryzen AI Max+ 395
Nominal VRAM
128 GB
Measured VRAM (avg)
22.76 GB
OS
Windows 11 23H2
Driver
AMD Adrenalin 25.10.1
CUDA
N/A
Power draw
105.4 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.38 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    66.99 tok/s

    Decode

    227.06 tok/s

    Prefill

    0.19 s

    TTFT

    22.76 GB

    VRAM

    —

    MTP

    105.4 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=24 running model_id=65 at Q4_K_M