Arao AI
Back to search results

gemma-4-E4B-it · IQ3_XS

Start a discussion
NVIDIA RTX 3060 12GB12GBvLLM v0.36L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_XS) on NVIDIA RTX 3060 12GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

89.05 tok/s

Decode

Decode speed

461.73 tok/s

Prefill

Prefill speed

0.57 s

TTFT

Time to first token

11.4 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. vLLM · IQ3_XS (current)Decode 89.05 · Prefill 461.73 ·
  2. Ollama · Q3_K_S Decode 79.42 · Prefill 278.2 ·

Core figures

Decode (avg)
89.05 tok/s
Prefill (avg)
461.73 tok/s
TTFT (avg)
0.57 s
VRAM (avg)
11.4 GB
MTP acceptance rate
—
TTFB
0.71 GB
Power draw
161.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ3_XS
Framework
vLLM
Version
v0.36
Context length
32768 tokens
Batch size
32
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
NVIDIA RTX 3060 12GB
Nominal VRAM
12 GB
Measured VRAM (avg)
11.4 GB
OS
Ubuntu 24.04
Driver
560.94
CUDA
12.6
Power draw
161.1 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 24.04 · CUDA 12.6 · 32768 ctx

    89.05 tok/s

    Decode

    461.73 tok/s

    Prefill

    0.57 s

    TTFT

    11.4 GB

    VRAM

    —

    MTP

    161.1 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=15 running model_id=67 at IQ3_XS