Arao AI
Back to search results

gemma-4-E4B-it · Q8_0

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.48L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-E4B-it (Q8_0) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

46.76 tok/s

Decode

Decode speed

225.72 tok/s

Prefill

Prefill speed

0.23 s

TTFT

Time to first token

11.76 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. vLLM · IQ3_S Decode 89.49 · Prefill 443.95 ·
  2. vLLM · Q8_0 (current)Decode 46.76 · Prefill 225.72 ·
  3. Ollama · IQ2_M Decode 83.45 · Prefill 389.24 ·
  4. Ollama · IQ3_S Decode 81.99 · Prefill 290.18 ·

Core figures

Decode (avg)
46.76 tok/s
Prefill (avg)
225.72 tok/s
TTFT (avg)
0.23 s
VRAM (avg)
11.76 GB
MTP acceptance rate
—
TTFB
0.37 GB
Power draw
47.7 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-E4B-it
Quantization
Q8_0
Framework
vLLM
Version
v0.48
Context length
32768 tokens
Batch size
8
GPU layers
999
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)
11.76 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
47.7 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

    v0.48 · JetPack 6.0 · CUDA 12.6 · 32768 ctx

    46.76 tok/s

    Decode

    225.72 tok/s

    Prefill

    0.23 s

    TTFT

    11.76 GB

    VRAM

    —

    MTP

    47.7 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=76 running model_id=67 at Q8_0