Arao AI
Back to search results

Qwen3-1.7B · FP16

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.46L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3-1.7B (FP16) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

57.65 tok/s

Decode

Decode speed

238.63 tok/s

Prefill

Prefill speed

1.79 s

TTFT

Time to first token

8.7 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 · FP16 (current)Decode 57.65 · Prefill 238.63 ·
  2. vLLM · IQ3_XS Decode 131.36 · Prefill 565.49 ·
  3. Strata · IQ2_M Decode 189.25 · Prefill 901.13 ·
  4. Strata · Q3_K_M Decode 175.11 · Prefill 755.7 ·
  5. Ollama · IQ2_M Decode 124.51 · Prefill 592.75 ·
  6. Ollama · IQ3_S Decode 119.35 · Prefill 527.63 ·
  7. Strata · IQ4_XS Decode 159.91 · Prefill 540.21 ·

Core figures

Decode (avg)
57.65 tok/s
Prefill (avg)
238.63 tok/s
TTFT (avg)
1.79 s
VRAM (avg)
8.7 GB
MTP acceptance rate
—
TTFB
0.46 GB
Power draw
16.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3-1.7B
Quantization
FP16
Framework
vLLM
Version
v0.46
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)
8.7 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
16.9 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

    v0.46 · JetPack 6.0 · CUDA 12.6 · 32768 ctx

    57.65 tok/s

    Decode

    238.63 tok/s

    Prefill

    1.79 s

    TTFT

    8.7 GB

    VRAM

    —

    MTP

    16.9 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=76 running model_id=55 at FP16