Armiger model bundle 3.11.0 — standalone INT8 ONNX
Model file: armiger.int8.onnx, 17,606,362 bytes (17.6 MB on disk).
Architecture: approximately 8 million parameters, byte-level RoPE transformer.
License: Apache-2.0. Model release.
This repository provides the CPU INT8 model. The Python example below uses the
GitHub package's ArmigerStandaloneONNX interface. It omits the Ultra catalogue
and swarm components. NumPy, ONNX Runtime and the package's other declared
dependencies are required; a GPU is not required.
Comparison charts
Latest published figures — provenance under review. These archived charts retain their original model labels and scores. Their displayed values and vector-based source records still need reconciliation; they do not establish verified current-release performance. These Ultra hybrid comparisons do not measure standalone INT8 accuracy or payload safety. Evaluation scope and source records.
Cloud teacher comparisons use separate common-support and swarm cohorts; panel-specific sample counts and metrics must remain separate.
Classifier and parser comparisons cover separate category, catalogue, language, metadata-screening and swarm tasks. Original PNGs and recorded results are unchanged.
Resources
17.6 MB is a file size, not a RAM requirement. Current-release standalone working RAM is not established by the public resource evidence. Ultra and the complete released SDK are different execution paths and can use substantially more memory. One complete-SDK CPU service with additional policy/reference data was observed near 2.1 GiB; that is not a measurement of this standalone API or a universal minimum. See resources and measurement scope.
Python quickstart
The quickstart uses software 3.12.2 with model bundle 3.11.0.
python -m pip install "armiger @ git+https://github.com/spencernorton/armiger.git@v3.12.2"
python -m armiger download --directory ./models-cpu --variant cpu
from armiger import ArmigerStandaloneONNX
model = ArmigerStandaloneONNX(
onnx_path="./models-cpu/armiger.int8.onnx",
vocab_path="./models-cpu/vocab.json",
calibration_path="./models-cpu/calibration.json",
)
result = model.predict({
"name": "Example.Movie.2001.1080p.WEB.x264",
"files": [{"path": "Example.Movie.2001.mkv", "size": 1_000_000_000}],
})
print(result["heads"]["category"])
Limits and evaluation status
Armiger classifies supplied metadata. Audio/subtitle, junk, adult-content and
honeypot outputs are predictions or policy flags. It does not listen to audio,
inspect media payloads, scan executable contents, certify lawful content, or
guarantee a safe or available download. Optional post-import ffprobe checks in
a connector are a separate operation.
Published comparison graphics are under provenance review: the displayed 3.11.0 / 2,484-item overview and its 3.0.0 / 2,835-item data receipt do not describe the same results. The latest published comparison charts are restored above as archival figures with that provenance limit. Detailed charts also combine newer aggregate values with older vector-based statistical panels. Their restored visibility does not establish current-release qualification. Historical hybrid results also do not establish the standalone neural path's accuracy. See evaluation status. No new balanced benchmark or universal accuracy, zero-leakage or safety rate is claimed here.
Sharing is optional. Payload filtering, encryption and signatures do not by themselves provide end-to-end anonymity or certify prediction accuracy. See the distributed-update and privacy limits.
Immutable historical revisions may retain earlier descriptions. This default model card and the linked evaluation/resource notes record the corrections; model files and immutable revisions are unchanged.