Arao AI
Back to search results

gemma-4-12B-it · IQ3_XS

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ3_XS) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

204.74 tok/s

Decode

Decode speed

1,066.91 tok/s

Prefill

Prefill speed

0.49 s

TTFT

Time to first token

17.72 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. Ollama · IQ3_XS (current)Decode 204.74 · Prefill 1066.91 ·
  2. Ollama · Q4_K_M Decode 162.15 · Prefill 852.94 ·
  3. Strata · Q4_K_S Decode 255.53 · Prefill 1120.66 ·

Core figures

Decode (avg)
204.74 tok/s
Prefill (avg)
1,066.91 tok/s
TTFT (avg)
0.49 s
VRAM (avg)
17.72 GB
MTP acceptance rate
—
TTFB
1.64 GB
Power draw
333.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ3_XS
Framework
Ollama
Version
v0.26
Context length
32768 tokens
Batch size
256
GPU layers
99
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)
17.72 GB
OS
Windows 11 23H2
Driver
565.57
CUDA
12.4
Power draw
333.4 W

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.26 · Windows 11 23H2 · CUDA 12.4 · 32768 ctx

    204.74 tok/s

    Decode

    1,066.91 tok/s

    Prefill

    0.49 s

    TTFT

    17.72 GB

    VRAM

    —

    MTP

    333.4 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=65 at IQ3_XS