Arao AI
Back to search results

gemma-4-31B-it · IQ3_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBStrata v0.31L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ3_XS) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

81.29 tok/s

Decode

Decode speed

414.62 tok/s

Prefill

Prefill speed

0.37 s

TTFT

Time to first token

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

Core figures

Decode (avg)
81.29 tok/s
Prefill (avg)
414.62 tok/s
TTFT (avg)
0.37 s
VRAM (avg)
42.46 GB
MTP acceptance rate
0.75
TTFB
0.65 GB
Power draw
117.2 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ3_XS
Framework
Strata
Version
v0.31
Context length
32768 tokens
Batch size
512
GPU layers
15
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)
42.46 GB
OS
Windows 11 23H2
Driver
AMD Adrenalin 25.10.1
CUDA
N/A
Power draw
117.2 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

    v0.31 · Windows 11 23H2 · CUDA N/A · 32768 ctx

    81.29 tok/s

    Decode

    414.62 tok/s

    Prefill

    0.37 s

    TTFT

    42.46 GB

    VRAM

    0.75

    MTP

    117.2 W

    Power draw

    L2 batch seed 2026-10-13: Strata on hw_id=24 running model_id=63 at IQ3_XS