Arao AI
Back to search results

gemma-4-31B-it · Q3_K_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-31B-it (Q3_K_M) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

26.56 tok/s

Decode

Decode speed

97.77 tok/s

Prefill

Prefill speed

0.29 s

TTFT

Time to first token

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

Core figures

Decode (avg)
26.56 tok/s
Prefill (avg)
97.77 tok/s
TTFT (avg)
0.29 s
VRAM (avg)
46.37 GB
MTP acceptance rate
—
TTFB
0.21 GB
Power draw
56.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-31B-it
Quantization
Q3_K_M
Framework
Ollama
Version
v0.34
Context length
16384 tokens
Batch size
512
GPU layers
20
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)
46.37 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
56.5 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

    v0.34 · JetPack 6.0 · CUDA 12.6 · 16384 ctx

    26.56 tok/s

    Decode

    97.77 tok/s

    Prefill

    0.29 s

    TTFT

    46.37 GB

    VRAM

    —

    MTP

    56.5 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=76 running model_id=63 at Q3_K_M