Arao AI
Back to search results

gemma-4-12B-it · IQ2_XS

Start a discussion
NVIDIA RTX 508016GBOllama v0.24L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_XS) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

103.79 tok/s

Decode

Decode speed

371.24 tok/s

Prefill

Prefill speed

1.66 s

TTFT

Time to first token

14.2 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

Today

Last verified

Performance

  1. Ollama · IQ2_XS (current)Decode 103.79 · Prefill 371.24 ·

Core figures

Decode (avg)
103.79 tok/s
Prefill (avg)
371.24 tok/s
TTFT (avg)
1.66 s
VRAM (avg)
14.2 GB
MTP acceptance rate
—
TTFB
0.83 GB
Power draw
282.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_XS
Framework
Ollama
Version
v0.24
Context length
32768 tokens
Batch size
256
GPU layers
33
Flash Attention
On

Hardware

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

GPU
NVIDIA RTX 5080
Nominal VRAM
16 GB
Measured VRAM (avg)
14.2 GB
OS
Ubuntu 22.04
Driver
560.94
CUDA
12.4
Power draw
282.1 W

Sources & evidence

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

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

    v0.24 · Ubuntu 22.04 · CUDA 12.4 · 32768 ctx

    103.79 tok/s

    Decode

    371.24 tok/s

    Prefill

    1.66 s

    TTFT

    14.2 GB

    VRAM

    —

    MTP

    282.1 W

    Power draw

    L2 batch seed 2026-10-10: Ollama on hw_id=14 running model_id=65 at IQ2_XS