Arao AI
Back to search results

gemma-4-E2B-it · Q6_K

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.54L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (Q6_K) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

70.66 tok/s

Decode

Decode speed

305.15 tok/s

Prefill

Prefill speed

1.82 s

TTFT

Time to first token

6.3 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. Ollama · Q6_K (current)Decode 70.66 · Prefill 305.15 ·
  2. Strata · IQ2_M Decode 176.21 · Prefill 663.99 ·
  3. Strata · IQ3_S Decode 167.92 · Prefill 544.11 ·

Core figures

Decode (avg)
70.66 tok/s
Prefill (avg)
305.15 tok/s
TTFT (avg)
1.82 s
VRAM (avg)
6.3 GB
MTP acceptance rate
—
TTFB
0.57 GB
Power draw
34.5 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
Q6_K
Framework
Ollama
Version
v0.54
Context length
4096 tokens
Batch size
256
GPU layers
20
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)
6.3 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
34.5 W

Sources & evidence

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

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-16

    v0.54 · JetPack 6.0 · CUDA 12.6 · 4096 ctx

    70.66 tok/s

    Decode

    305.15 tok/s

    Prefill

    1.82 s

    TTFT

    6.3 GB

    VRAM

    —

    MTP

    34.5 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=76 running model_id=66 at Q6_K