Arao AI
Back to search results

Qwen3.5-0.8B · IQ3_S

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.52L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-0.8B (IQ3_S) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

138.5 tok/s

Decode

Decode speed

456.82 tok/s

Prefill

Prefill speed

0.37 s

TTFT

Time to first token

3.21 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 177.54 · Prefill 614.93 ·
  2. llama.cpp · IQ2_XS Decode 200.96 · Prefill 773.99 ·
  3. Ollama · IQ3_S (current)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 Decode 125.95 · Prefill 424.45 ·

Core figures

Decode (avg)
138.5 tok/s
Prefill (avg)
456.82 tok/s
TTFT (avg)
0.37 s
VRAM (avg)
3.21 GB
MTP acceptance rate
—
TTFB
1.11 GB
Power draw
16.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-0.8B
Quantization
IQ3_S
Framework
Ollama
Version
v0.52
Context length
2048 tokens
Batch size
256
GPU layers
99
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)
3.21 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
16.4 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

    v0.52 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    138.5 tok/s

    Decode

    456.82 tok/s

    Prefill

    0.37 s

    TTFT

    3.21 GB

    VRAM

    —

    MTP

    16.4 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=76 running model_id=51 at IQ3_S