Arao AI
Back to search results

gemma-4-31B-it · Q3_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBStrata v0.41L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q3_K_S) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

82.27 tok/s

Decode

Decode speed

338.79 tok/s

Prefill

Prefill speed

2.46 s

TTFT

Time to first token

44.41 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Strata · IQ3_XS Decode 81.29 · Prefill 414.62 ·
  2. Strata · Q3_K_S (current)Decode 82.27 · Prefill 338.79 ·

Core figures

Decode (avg)
82.27 tok/s
Prefill (avg)
338.79 tok/s
TTFT (avg)
2.46 s
VRAM (avg)
44.41 GB
MTP acceptance rate
0.66
TTFB
0.66 GB
Power draw
133.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q3_K_S
Framework
Strata
Version
v0.41
Context length
16384 tokens
Batch size
512
GPU layers
8
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)
44.41 GB
OS
Windows 11 23H2
Driver
AMD Adrenalin 25.10.1
CUDA
N/A
Power draw
133.6 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

    v0.41 · Windows 11 23H2 · CUDA N/A · 16384 ctx

    82.27 tok/s

    Decode

    338.79 tok/s

    Prefill

    2.46 s

    TTFT

    44.41 GB

    VRAM

    0.66

    MTP

    133.6 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=24 running model_id=63 at Q3_K_S