Arao AI
Back to search results

gemma-4-12B-it · IQ2_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of gemma-4-12B-it (IQ2_M) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

67.16 tok/s

Decode

Decode speed

321.62 tok/s

Prefill

Prefill speed

0.74 s

TTFT

Time to first token

15.2 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 · IQ2_M (current)Decode 67.16 · Prefill 321.62 ·
  2. Ollama · Q2_K Decode 51.17 · Prefill 196.24 ·

Core figures

Decode (avg)
67.16 tok/s
Prefill (avg)
321.62 tok/s
TTFT (avg)
0.74 s
VRAM (avg)
15.2 GB
MTP acceptance rate
—
TTFB
0.54 GB
Power draw
57 W

Configuration

Member-level fields are taken from the most recent run

Model
gemma-4-12B-it
Quantization
IQ2_M
Framework
vLLM
Version
v0.30
Context length
16384 tokens
Batch size
32
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)
15.2 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
57 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

    v0.30 · JetPack 6.0 · CUDA 12.6 · 16384 ctx

    67.16 tok/s

    Decode

    321.62 tok/s

    Prefill

    0.74 s

    TTFT

    15.2 GB

    VRAM

    —

    MTP

    57 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=76 running model_id=65 at IQ2_M