Arao AI
Back to search results

gemma-4-31B-it · IQ3_XS

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.35L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (IQ3_XS) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

29.45 tok/s

Decode

Decode speed

108.81 tok/s

Prefill

Prefill speed

0.33 s

TTFT

Time to first token

42.46 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. Ollama · IQ3_XS (current)Decode 29.45 · Prefill 108.81 ·
  2. Ollama · Q3_K_M Decode 26.56 · Prefill 97.77 ·

Core figures

Decode (avg)
29.45 tok/s
Prefill (avg)
108.81 tok/s
TTFT (avg)
0.33 s
VRAM (avg)
42.46 GB
MTP acceptance rate
—
TTFB
0.24 GB
Power draw
32.1 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
IQ3_XS
Framework
Ollama
Version
v0.35
Context length
2048 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 Jetson AGX Orin 64GB
Nominal VRAM
64 GB
Measured VRAM (avg)
42.46 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
32.1 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-13

    v0.35 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    29.45 tok/s

    Decode

    108.81 tok/s

    Prefill

    0.33 s

    TTFT

    42.46 GB

    VRAM

    —

    MTP

    32.1 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=76 running model_id=63 at IQ3_XS