Arao AI
Back to search results

Qwen3.5-0.8B · Q5_K_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBvLLM v0.32L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (Q5_K_M) on NVIDIA Jetson AGX Orin 64GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.

125.95 tok/s

Decode

Decode speed

424.45 tok/s

Prefill

Prefill speed

1.38 s

TTFT

Time to first token

3.66 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 177.54 · Prefill 614.93 ·
  2. llama.cpp · IQ2_XS Decode 200.96 · Prefill 773.99 ·
  3. Ollama · IQ3_S Decode 138.5 · Prefill 456.82 ·
  4. Ollama · Q5_K_S Decode 116.4 · Prefill 439.62 ·
  5. vLLM · IQ4_XS Decode 140.75 · Prefill 759.45 ·
  6. vLLM · Q5_K_M (current)Decode 125.95 · Prefill 424.45 ·

Core figures

Decode (avg)
125.95 tok/s
Prefill (avg)
424.45 tok/s
TTFT (avg)
1.38 s
VRAM (avg)
3.66 GB
MTP acceptance rate
—
TTFB
1.01 GB
Power draw
30 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
Q5_K_M
Framework
vLLM
Version
v0.32
Context length
2048 tokens
Batch size
16
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)
3.66 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
30 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

    v0.32 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    125.95 tok/s

    Decode

    424.45 tok/s

    Prefill

    1.38 s

    TTFT

    3.66 GB

    VRAM

    —

    MTP

    30 W

    Power draw

    L2 batch seed 2026-10-13: vLLM on hw_id=76 running model_id=51 at Q5_K_M