Arao AI
Back to search results

gemma-4-E4B-it · Q3_K_S

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q3_K_S) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

163.73 tok/s

Decode

Decode speed

675.44 tok/s

Prefill

Prefill speed

0.46 s

TTFT

Time to first token

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

Core figures

Decode (avg)
163.73 tok/s
Prefill (avg)
675.44 tok/s
TTFT (avg)
0.46 s
VRAM (avg)
7.56 GB
MTP acceptance rate
—
TTFB
1.31 GB
Power draw
86.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q3_K_S
Framework
vLLM
Version
v0.35
Context length
8192 tokens
Batch size
32
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)
7.56 GB
OS
Windows 11 23H2
Driver
560.94
CUDA
N/A
Power draw
86.7 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

    v0.35 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    163.73 tok/s

    Decode

    675.44 tok/s

    Prefill

    0.46 s

    TTFT

    7.56 GB

    VRAM

    —

    MTP

    86.7 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=24 running model_id=67 at Q3_K_S