Arao AI
Back to search results

Qwen3-4B · IQ2_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.39L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ2_M) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

96.3 tok/s

Decode

Decode speed

512.46 tok/s

Prefill

Prefill speed

1.22 s

TTFT

Time to first token

6.47 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

2 days ago

Last verified

Performance

  1. llama.cpp · IQ2_M Decode 92.76 · Prefill 306.43 ·
  2. vLLM · IQ2_M (current)Decode 96.3 · Prefill 512.46 ·
  3. vLLM · Q2_K Decode 95.78 · Prefill 454.64 ·
  4. Ollama · IQ3_S Decode 73.25 · Prefill 282.68 ·
  5. Ollama · Q4_K_M Decode 58.47 · Prefill 300.76 ·

Core figures

Decode (avg)
96.3 tok/s
Prefill (avg)
512.46 tok/s
TTFT (avg)
1.22 s
VRAM (avg)
6.47 GB
MTP acceptance rate
—
TTFB
0.77 GB
Power draw
48.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ2_M
Framework
vLLM
Version
v0.39
Context length
16384 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)
6.47 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
48.2 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

    v0.39 · JetPack 6.0 · CUDA 12.6 · 16384 ctx

    96.3 tok/s

    Decode

    512.46 tok/s

    Prefill

    1.22 s

    TTFT

    6.47 GB

    VRAM

    —

    MTP

    48.2 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=76 running model_id=54 at IQ2_M