Downloads · 30 days
0
brevox-gemma-3-4b-ane
robertteleng/brevox-gemma-3-4b-ane
brevox-gemma-3-4b-ane is a machine learning model from robertteleng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Archived Core ML bundle used by Brevox as the on-device fallback summarizer when Apple FoundationModels rejects a given recording via its non-bypassable safety guardrails.
Access
Public
Updated Apr 23, 2026
Repo size
8.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.aar4.1 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Apr 23, 2026
- Updated
- Apr 23, 2026
- SHA
- 06164c8c
Base models
Model card
From the Hugging Face model README
Brevox — Gemma 3 4B IT (ANE) Asset
Archived Core ML bundle used by Brevox as the on-device fallback summarizer when Apple FoundationModels rejects a given recording via its non-bypassable safety guardrails.
This repository only hosts the distribution artifact (the .aar file) for
the Brevox iOS/macOS app's runtime download. It is not the source of the
conversion pipeline nor a redistribution of upstream Google weights in their
original form.
What is this?
A single Apple Archive (.aar, LZFSE-compressed) containing a Core ML 3-stage
runner of Gemma 3 4B IT (int4 QAT, 4096 context) converted by
ANEMLL. Extracted at runtime into
~/Library/Application Support/Brevox/Models/Summarizer_Gemma3_4B/.
| Field | Value |
|---|---|
| File | Summarizer_Gemma3_4B.aar |
| Size | ~3.85 GB (3,940 MB) |
| SHA-256 | 9fcd4c09ca3d66d3d15e60c8a2f212deabf648489d2d41f9d9a7ab3e6aef7fb1 |
| Compression | Apple Archive, LZFSE |
| Contents | 5 .mlmodelc (embeddings + 3 FFN chunks + lm_head) + tokenizer.json + tokenizer.model + config.json + meta.yaml |
| Converted by | ANEMLL v0.3.5 |
| Target hardware | Apple A17 Pro / M-series with Neural Engine |
Provenance
- Upstream weights:
google/gemma-3-4b-it(QAT int4-unquantized variant). - Conversion to Core ML by ANEMLL:
anemll/anemll-google-gemma-3-4b-it-qat-int4-unquantized-ctx4096. - Packaged into a single LZFSE Apple Archive for delivery via Brevox's
ModelDeliveryService(URLSession+ Range resume + streaming SHA-256 + AppleArchive extraction).
Licensing
- Weights: governed by the Gemma Terms of Use and the Gemma Prohibited Use Policy. By downloading or using this asset you agree to those terms.
- Conversion pipeline: ANEMLL, MIT License.
- Packaging wrapper (this repo's
.aar): MIT, trivially derivative.
Why Hugging Face and not GitHub Releases
GitHub Releases caps individual asset size at 2 GB. The packaged bundle is 3.85 GB. Hugging Face's LFS-backed storage and anonymous CDN distribution are the appropriate hosting choice.
Usage (app side)
Brevox fetches the asset at:
https://huggingface.co/robertteleng/brevox-gemma-3-4b-ane/resolve/main/Summarizer_Gemma3_4B.aar
Manual verification:
shasum -a 256 Summarizer_Gemma3_4B.aar
# expected: 9fcd4c09ca3d66d3d15e60c8a2f212deabf648489d2d41f9d9a7ab3e6aef7fb1
- License
- other
- Created
- Apr 23, 2026
- Updated
- Apr 23, 2026