Arao AI
Back to search results

gemma-4-E4B-it · IQ4_XS

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.37L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ4_XS) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

142.31 tok/s

Decode

Decode speed

714.99 tok/s

Prefill

Prefill speed

0.35 s

TTFT

Time to first token

8.32 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ4_XS (current)Decode 142.31 · Prefill 714.99 ·
  2. vLLM · Q3_K_S Decode 163.73 · Prefill 675.44 ·
  3. Strata · IQ2_XS Decode 273.72 · Prefill 1347.27 ·

Core figures

Decode (avg)
142.31 tok/s
Prefill (avg)
714.99 tok/s
TTFT (avg)
0.35 s
VRAM (avg)
8.32 GB
MTP acceptance rate
—
TTFB
1.14 GB
Power draw
75.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ4_XS
Framework
vLLM
Version
v0.37
Context length
8192 tokens
Batch size
8
GPU layers
999
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)
8.32 GB
OS
macOS 15.0
Driver
560.94
CUDA
N/A
Power draw
75.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.37 · macOS 15.0 · CUDA N/A · 8192 ctx

    142.31 tok/s

    Decode

    714.99 tok/s

    Prefill

    0.35 s

    TTFT

    8.32 GB

    VRAM

    —

    MTP

    75.1 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=24 running model_id=67 at IQ4_XS