Arao AI
Back to search results

gemma-4-E4B-it · IQ3_XS

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBvLLM v0.29L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ3_XS) on NVIDIA RTX PRO 6000 Blackwell 96GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

344.94 tok/s

Decode

Decode speed

1,590.34 tok/s

Prefill

Prefill speed

2.16 s

TTFT

Time to first token

12.52 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

12 days ago

Last verified

Performance

  1. vLLM · IQ3_XS (current)Decode 344.94 · Prefill 1590.34 ·
  2. Ollama · IQ2_XS Decode 387.68 · Prefill 2077.1 ·

Core figures

Decode (avg)
344.94 tok/s
Prefill (avg)
1,590.34 tok/s
TTFT (avg)
2.16 s
VRAM (avg)
12.52 GB
MTP acceptance rate
—
TTFB
2.76 GB
Power draw
393.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ3_XS
Framework
vLLM
Version
v0.29
Context length
32768 tokens
Batch size
32
GPU layers
999
Flash Attention
Off

Hardware

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

GPU
NVIDIA RTX PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
12.52 GB
OS
Windows 11 23H2
Driver
572.83
CUDA
12.8
Power draw
393.1 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

    v0.29 · Windows 11 23H2 · CUDA 12.8 · 32768 ctx

    344.94 tok/s

    Decode

    1,590.34 tok/s

    Prefill

    2.16 s

    TTFT

    12.52 GB

    VRAM

    —

    MTP

    393.1 W

    Power draw

    L2 batch seed 2026-10-24: vLLM on hw_id=68 running model_id=67 at IQ3_XS