Arao AI
Back to search results

gemma-4-E4B-it · IQ3_XS

Start a discussion
AMD Strix Point (Radeon 890M)vLLM v0.22L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_XS) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

93.71 tok/s

Decode

Decode speed

479.79 tok/s

Prefill

Prefill speed

1.46 s

TTFT

Time to first token

7.31 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 · IQ3_XS (current)Decode 93.71 · Prefill 479.79 ·
  2. vLLM · Q6_K Decode 56.27 · Prefill 255.06 ·
  3. Ollama · Q2_K Decode 85.31 · Prefill 404.47 ·

Core figures

Decode (avg)
93.71 tok/s
Prefill (avg)
479.79 tok/s
TTFT (avg)
1.46 s
VRAM (avg)
7.31 GB
MTP acceptance rate
—
TTFB
0.75 GB
Power draw
51.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ3_XS
Framework
vLLM
Version
v0.22
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 Strix Point (Radeon 890M)
Measured VRAM (avg)
7.31 GB
OS
Windows 11 23H2
Driver
amdgpu 6.10
CUDA
N/A
Power draw
51.8 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

    v0.22 · Windows 11 23H2 · CUDA N/A · 8192 ctx

    93.71 tok/s

    Decode

    479.79 tok/s

    Prefill

    1.46 s

    TTFT

    7.31 GB

    VRAM

    —

    MTP

    51.8 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=67 at IQ3_XS