Arao AI
Back to search results

Qwen3.5-4B · Q3_K_M

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBOllama v0.34L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen3.5-4B (Q3_K_M) on NVIDIA Jetson AGX Orin 64GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.

81.64 tok/s

Decode

Decode speed

331.85 tok/s

Prefill

Prefill speed

0.12 s

TTFT

Time to first token

7.81 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 96.05 · Prefill 357.59 ·
  2. Ollama · Q3_K_M (current)Decode 81.64 · Prefill 331.85 ·
  3. llama.cpp · IQ3_S Decode 86 · Prefill 348.05 ·
  4. llama.cpp · Q3_K_M Decode 81.53 · Prefill 347.31 ·
  5. Strata · Q3_K_S Decode 126.8 · Prefill 658.95 ·
  6. Strata · Q5_K_S Decode 96.92 · Prefill 440.11 ·

Core figures

Decode (avg)
81.64 tok/s
Prefill (avg)
331.85 tok/s
TTFT (avg)
0.12 s
VRAM (avg)
7.81 GB
MTP acceptance rate
—
TTFB
0.65 GB
Power draw
53.2 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen3.5-4B
Quantization
Q3_K_M
Framework
Ollama
Version
v0.34
Context length
16384 tokens
Batch size
256
GPU layers
28
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)
7.81 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
53.2 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

    v0.34 · JetPack 6.0 · CUDA 12.6 · 16384 ctx

    81.64 tok/s

    Decode

    331.85 tok/s

    Prefill

    0.12 s

    TTFT

    7.81 GB

    VRAM

    —

    MTP

    53.2 W

    Power draw

    L2 batch seed 2026-10-16: Ollama on hw_id=76 running model_id=48 at Q3_K_M