Arao AI
Back to search results

gemma-4-26B-A4B-it · Q8_0

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.26L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (Q8_0) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

24.68 tok/s

Decode

Decode speed

116.33 tok/s

Prefill

Prefill speed

0.92 s

TTFT

Time to first token

60.8 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

  1. vLLM · IQ4_XS Decode 42.78 · Prefill 174.63 ·
  2. vLLM · Q5_K_S Decode 34.07 · Prefill 117.53 ·
  3. Ollama · Q8_0 (current)Decode 24.68 · Prefill 116.33 ·

Core figures

Decode (avg)
24.68 tok/s
Prefill (avg)
116.33 tok/s
TTFT (avg)
0.92 s
VRAM (avg)
60.8 GB
MTP acceptance rate
—
TTFB
0.2 GB
Power draw
46.3 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-26B-A4B-it
Quantization
Q8_0
Framework
Ollama
Version
v0.26
Context length
2048 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 Jetson AGX Orin 64GB
Nominal VRAM
64 GB
Measured VRAM (avg)
60.8 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
46.3 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

    v0.26 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    24.68 tok/s

    Decode

    116.33 tok/s

    Prefill

    0.92 s

    TTFT

    60.8 GB

    VRAM

    —

    MTP

    46.3 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=76 running model_id=64 at Q8_0