Arao AI
Back to search results

gemma-4-E4B-it · Q3_K_M

Start a discussion
NVIDIA RTX 409024GBOllama v0.36L2 Cross-framework verified

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

158.5 tok/s

Decode

Decode speed

719.84 tok/s

Prefill

Prefill speed

0.55 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

11 days ago

Last verified

Performance

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

Core figures

Decode (avg)
158.5 tok/s
Prefill (avg)
719.84 tok/s
TTFT (avg)
0.55 s
VRAM (avg)
13.52 GB
MTP acceptance rate
—
TTFB
1.27 GB
Power draw
386.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q3_K_M
Framework
Ollama
Version
v0.36
Context length
8192 tokens
Batch size
256
GPU layers
99
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
570.86
CUDA
12.4
Power draw
386.1 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

    v0.36 · Ubuntu 22.04 · CUDA 12.4 · 8192 ctx

    158.5 tok/s

    Decode

    719.84 tok/s

    Prefill

    0.55 s

    TTFT

    13.52 GB

    VRAM

    —

    MTP

    386.1 W

    Power draw

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