Arao AI
Back to search results

Qwen3.8-9B · FP16

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

This page aggregates 1 real-world runs of Qwen3.8-9B (FP16) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

29.45 tok/s

Decode

Decode speed

126.06 tok/s

Prefill

Prefill speed

2.27 s

TTFT

Time to first token

37.06 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 29.45 · Prefill 126.06 ·
  2. vLLM · Q5_K_M Decode 44.26 · Prefill 164.08 ·
  3. Strata · IQ2_M Decode 107.61 · Prefill 409.38 ·
  4. vLLM · IQ3_S Decode 60.53 · Prefill 223.41 ·

Core figures

Decode (avg)
29.45 tok/s
Prefill (avg)
126.06 tok/s
TTFT (avg)
2.27 s
VRAM (avg)
37.06 GB
MTP acceptance rate
—
TTFB
0.24 GB
Power draw
41.5 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.8-9B
Quantization
FP16
Framework
vLLM
Version
v0.46
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)
37.06 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
41.5 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 · 16384 ctx

    29.45 tok/s

    Decode

    126.06 tok/s

    Prefill

    2.27 s

    TTFT

    37.06 GB

    VRAM

    —

    MTP

    41.5 W

    Power draw

    L2 batch seed 2026-10-16: vLLM on hw_id=76 running model_id=52 at FP16