Arao AI
Back to search results

gemma-4-E2B-it · IQ1_S

Start a discussion
AMD Ryzen AI Max+ 395128GBvLLM v0.27L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ1_S) on AMD Ryzen AI Max+ 395 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

291.55 tok/s

Decode

Decode speed

1,102.46 tok/s

Prefill

Prefill speed

1.52 s

TTFT

Time to first token

3.86 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · Q3_K_M Decode 208.76 · Prefill 678.14 ·
  2. vLLM · IQ1_S (current)Decode 291.55 · Prefill 1102.46 ·

Core figures

Decode (avg)
291.55 tok/s
Prefill (avg)
1,102.46 tok/s
TTFT (avg)
1.52 s
VRAM (avg)
3.86 GB
MTP acceptance rate
—
TTFB
2.33 GB
Power draw
111.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
IQ1_S
Framework
vLLM
Version
v0.27
Context length
8192 tokens
Batch size
8
GPU layers
999
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)
3.86 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
N/A
Power draw
111.8 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

    v0.27 · Ubuntu 22.04 · CUDA N/A · 8192 ctx

    291.55 tok/s

    Decode

    1,102.46 tok/s

    Prefill

    1.52 s

    TTFT

    3.86 GB

    VRAM

    —

    MTP

    111.8 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=24 running model_id=66 at IQ1_S