Arao AI
Back to search results

gemma-4-E4B-it · Q3_K_M

Start a discussion
NVIDIA RTX 409024GBStrata v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q3_K_M) on NVIDIA RTX 4090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

243.76 tok/s

Decode

Decode speed

1,261.12 tok/s

Prefill

Prefill speed

2.02 s

TTFT

Time to first token

13.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. Ollama · Q3_K_M Decode 158.5 · Prefill 719.84 ·
  2. Strata · Q3_K_M (current)Decode 243.76 · Prefill 1261.12 ·

Core figures

Decode (avg)
243.76 tok/s
Prefill (avg)
1,261.12 tok/s
TTFT (avg)
2.02 s
VRAM (avg)
13.52 GB
MTP acceptance rate
0.75
TTFB
1.95 GB
Power draw
317.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q3_K_M
Framework
Strata
Version
v0.34
Context length
16384 tokens
Batch size
512
GPU layers
15
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 4090
Nominal VRAM
24 GB
Measured VRAM (avg)
13.52 GB
OS
Ubuntu 22.04
Driver
572.83
CUDA
12.8
Power draw
317.6 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

    v0.34 · Ubuntu 22.04 · CUDA 12.8 · 16384 ctx

    243.76 tok/s

    Decode

    1,261.12 tok/s

    Prefill

    2.02 s

    TTFT

    13.52 GB

    VRAM

    0.75

    MTP

    317.6 W

    Power draw

    L2 batch seed 2026-10-24: Strata on hw_id=1 running model_id=67 at Q3_K_M