Arao AI
Back to search results

gemma-4-31B-it · IQ1_S

Start a discussion
NVIDIA RTX PRO 6000 Blackwell 96GB96GBOllama v0.47L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ1_S) on NVIDIA RTX PRO 6000 Blackwell 96GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

184.42 tok/s

Decode

Decode speed

842.53 tok/s

Prefill

Prefill speed

0.62 s

TTFT

Time to first token

29.44 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

17 days ago

Last verified

Performance

  1. vLLM · IQ2_XS Decode 189.85 · Prefill 737.75 ·
  2. Ollama · IQ1_S (current)Decode 184.42 · Prefill 842.53 ·
  3. Ollama · Q4_K_S Decode 134.3 · Prefill 614.37 ·

Core figures

Decode (avg)
184.42 tok/s
Prefill (avg)
842.53 tok/s
TTFT (avg)
0.62 s
VRAM (avg)
29.44 GB
MTP acceptance rate
—
TTFB
1.48 GB
Power draw
330.8 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ1_S
Framework
Ollama
Version
v0.47
Context length
16384 tokens
Batch size
512
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 PRO 6000 Blackwell 96GB
Nominal VRAM
96 GB
Measured VRAM (avg)
29.44 GB
OS
Ubuntu 24.04
Driver
565.57
CUDA
12.8
Power draw
330.8 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

    v0.47 · Ubuntu 24.04 · CUDA 12.8 · 16384 ctx

    184.42 tok/s

    Decode

    842.53 tok/s

    Prefill

    0.62 s

    TTFT

    29.44 GB

    VRAM

    —

    MTP

    330.8 W

    Power draw

    L2 batch seed 2026-10-19: Ollama on hw_id=68 running model_id=63 at IQ1_S