Arao AI
Back to search results

gemma-4-E4B-it · IQ2_XS

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (IQ2_XS) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

387.68 tok/s

Decode

Decode speed

2,077.1 tok/s

Prefill

Prefill speed

1.62 s

TTFT

Time to first token

10.16 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 Decode 344.94 · Prefill 1590.34 ·
  2. Ollama · IQ2_XS (current)Decode 387.68 · Prefill 2077.1 ·

Core figures

Decode (avg)
387.68 tok/s
Prefill (avg)
2,077.1 tok/s
TTFT (avg)
1.62 s
VRAM (avg)
10.16 GB
MTP acceptance rate
—
TTFB
3.1 GB
Power draw
344.6 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
IQ2_XS
Framework
Ollama
Version
v0.44
Context length
4096 tokens
Batch size
256
GPU layers
20
Flash Attention
On

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)
10.16 GB
OS
Windows 11 23H2
Driver
570.86
CUDA
12.8
Power draw
344.6 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

    v0.44 · Windows 11 23H2 · CUDA 12.8 · 4096 ctx

    387.68 tok/s

    Decode

    2,077.1 tok/s

    Prefill

    1.62 s

    TTFT

    10.16 GB

    VRAM

    —

    MTP

    344.6 W

    Power draw

    L2 batch seed 2026-10-24: Ollama on hw_id=68 running model_id=67 at IQ2_XS