Arao AI
Back to search results

Qwen2.5-0.5B-Instruct · IQ1_S

Start a discussion
NVIDIA Jetson AGX Orin 64GB64GBllama.cpp v0.23L2 Cross-framework verified

This page aggregates 1 real-world runs of Qwen2.5-0.5B-Instruct (IQ1_S) on NVIDIA Jetson AGX Orin 64GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.

243.52 tok/s

Decode

Decode speed

900.17 tok/s

Prefill

Prefill speed

1.32 s

TTFT

Time to first token

2.54 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 · IQ1_S (current)Decode 243.52 · Prefill 900.17 ·
  2. llama.cpp · Q3_K_S Decode 199.9 · Prefill 998.9 ·
  3. Strata · IQ3_XS Decode 310.9 · Prefill 1483.77 ·
  4. Strata · IQ2_M Decode 337.39 · Prefill 1690.81 ·

Core figures

Decode (avg)
243.52 tok/s
Prefill (avg)
900.17 tok/s
TTFT (avg)
1.32 s
VRAM (avg)
2.54 GB
MTP acceptance rate
—
TTFB
1.95 GB
Power draw
20.9 W

Configuration

Member-level fields are taken from the most recent run

Model
Qwen2.5-0.5B-Instruct
Quantization
IQ1_S
Framework
llama.cpp
Version
v0.23
Context length
2048 tokens
Batch size
256
GPU layers
20
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)
2.54 GB
OS
JetPack 6.0
Driver
NVIDIA L4T 36.3
CUDA
12.6
Power draw
20.9 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

    v0.23 · JetPack 6.0 · CUDA 12.6 · 2048 ctx

    243.52 tok/s

    Decode

    900.17 tok/s

    Prefill

    1.32 s

    TTFT

    2.54 GB

    VRAM

    —

    MTP

    20.9 W

    Power draw

    L2 batch seed 2026-10-16: llama.cpp on hw_id=76 running model_id=59 at IQ1_S