Arao AI
Back to search results

gemma-4-12B-it · Q8_0

Start a discussion
AMD Ryzen AI Max+ 395128GBStrata v0.45L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (Q8_0) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

71.19 tok/s

Decode

Decode speed

287.95 tok/s

Prefill

Prefill speed

2.4 s

TTFT

Time to first token

31.08 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 Decode 66.99 · Prefill 227.06 ·
  2. Strata · Q8_0 (current)Decode 71.19 · Prefill 287.95 ·

Core figures

Decode (avg)
71.19 tok/s
Prefill (avg)
287.95 tok/s
TTFT (avg)
2.4 s
VRAM (avg)
31.08 GB
MTP acceptance rate
0.63
TTFB
0.57 GB
Power draw
113 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
Q8_0
Framework
Strata
Version
v0.45
Context length
2048 tokens
Batch size
512
GPU layers
5
Flash Attention
On

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)
31.08 GB
OS
Windows 11 23H2
Driver
AMD Adrenalin 25.10.1
CUDA
N/A
Power draw
113 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

    v0.45 · Windows 11 23H2 · CUDA N/A · 2048 ctx

    71.19 tok/s

    Decode

    287.95 tok/s

    Prefill

    2.4 s

    TTFT

    31.08 GB

    VRAM

    0.63

    MTP

    113 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=24 running model_id=65 at Q8_0