Arao AI
Back to search results

gemma-4-E2B-it · IQ2_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBStrata v0.40L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E2B-it (IQ2_M) on NVIDIA Jetson AGX Orin 64GB with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

176.21 tok/s

Decode

Decode speed

663.99 tok/s

Prefill

Prefill speed

0.99 s

TTFT

Time to first token

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

Core figures

Decode (avg)
176.21 tok/s
Prefill (avg)
663.99 tok/s
TTFT (avg)
0.99 s
VRAM (avg)
4.28 GB
MTP acceptance rate
0.59
TTFB
1.41 GB
Power draw
47.4 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E2B-it
Quantization
IQ2_M
Framework
Strata
Version
v0.40
Context length
8192 tokens
Batch size
1024
GPU layers
8
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)
4.28 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
47.4 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

    v0.40 · JetPack 6.0 · CUDA 12.6 · 8192 ctx

    176.21 tok/s

    Decode

    663.99 tok/s

    Prefill

    0.99 s

    TTFT

    4.28 GB

    VRAM

    0.59

    MTP

    47.4 W

    Power draw

    L2 batch seed 2026-10-16: Strata on hw_id=76 running model_id=66 at IQ2_M