Arao AI
Back to search results

Qwen3-4B · IQ3_S

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.44L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-4B (IQ3_S) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

73.25 tok/s

Decode

Decode speed

282.68 tok/s

Prefill

Prefill speed

2.08 s

TTFT

Time to first token

7.64 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

5 days ago

Last verified

Performance

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

Core figures

Decode (avg)
73.25 tok/s
Prefill (avg)
282.68 tok/s
TTFT (avg)
2.08 s
VRAM (avg)
7.64 GB
MTP acceptance rate
—
TTFB
0.59 GB
Power draw
51 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-4B
Quantization
IQ3_S
Framework
Ollama
Version
v0.44
Context length
16384 tokens
Batch size
512
GPU layers
33
Flash Attention
Off

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)
7.64 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
51 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

    v0.44 · JetPack 6.0 · CUDA 12.6 · 16384 ctx

    73.25 tok/s

    Decode

    282.68 tok/s

    Prefill

    2.08 s

    TTFT

    7.64 GB

    VRAM

    —

    MTP

    51 W

    Power draw

    L2 batch seed 2026-10-13: Ollama on hw_id=76 running model_id=54 at IQ3_S