Arao AI
Back to search results

gemma-4-E4B-it · IQ4_XS

Start a discussion
NVIDIA RTX 508016GBStrata v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ4_XS) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

314.5 tok/s

Decode

Decode speed

1,280.69 tok/s

Prefill

Prefill speed

1.1 s

TTFT

Time to first token

14.53 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

11 days ago

Last verified

Performance

  1. vLLM · IQ2_XS Decode 301.33 · Prefill 1596.94 ·
  2. Strata · IQ4_XS (current)Decode 314.5 · Prefill 1280.69 ·

Core figures

Decode (avg)
314.5 tok/s
Prefill (avg)
1,280.69 tok/s
TTFT (avg)
1.1 s
VRAM (avg)
14.53 GB
MTP acceptance rate
0.78
TTFB
2.52 GB
Power draw
314.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ4_XS
Framework
Strata
Version
v0.32
Context length
8192 tokens
Batch size
256
GPU layers
5
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
14.53 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.6
Power draw
314.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-24

    v0.32 · Windows 11 23H2 · CUDA 12.6 · 8192 ctx

    314.5 tok/s

    Decode

    1,280.69 tok/s

    Prefill

    1.1 s

    TTFT

    14.53 GB

    VRAM

    0.78

    MTP

    314.5 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=14 running model_id=67 at IQ4_XS