ModelListedExternal

Nemotron Ocr v2 Coreml

nvidia-open-model-license

Sourcehuggingface.co/mweinbach/nemotron-ocr-v2-coreml/tree/3f48f92186b307341c4727a9281ca5cc33eefef8

KindOtherBase modelnvidia/nemotron-ocr-v2VersionRevision 3f48f92Unratedgrade

Model source

Kind: Other
File size: 4.00 KB–68.9 MB
Base model: nvidia/nemotron-ocr-v2
Version: vRevision 3f48f92
Updated: Nov 5, 2026
Downloads: 76
Source: Hugging Face

Source description

Nemotron OCR v2 — CoreML (Apple Neural Engine)

CoreML-format models for NVIDIA Nemotron OCR v2, exported for native Apple Silicon inference targeting the Apple Neural Engine (ANE).

Model Details

Three-stage OCR pipeline optimized for ANE acceleration:

Component	Format	Precision	Size
Detector	`.mlmodel`	float32	~181 MB
Recognizer	`.mlpackage`	float16	~12–72 MB
Relational	`.mlpackage`	float16	~5 MB

Variants

Variant	Charset	Detector Resolution	Batch Size
`v2_english`	855 characters	1024×1024	16 regions
`v2_multilingual`	~42K characters	1024×1024	16 regions

ANE Performance

On Apple Silicon, the CoreML ANE path provides the lowest latency:

Backend	Typical Latency	Device
CoreML ANE	~350ms	Apple Neural Engine
MLX GPU	~2800ms	Metal GPU
MLX CPU	~6700ms	CPU

Usage with SwiftNemotronOCR

This model is designed for use with SwiftNemotronOCR, an all-Swift OCR pipeline.

Quick Start

# Clone the Swift package
git clone https://github.com/mweinbach/SwiftNemotronOCR.git
cd SwiftNemotronOCR

# Build
swift build -c release

# Download this model
# Place v2_english/ and/or v2_multilingual/ under a model/coreml/ directory

# Run OCR on ANE
.build/release/apple-ocr-runner \
  --runtime coreml \
  --device ANE \
  --model-dir /path/to/model/coreml \
  --image /path/to/image.png \
  --variant en \
  --level paragraph

Supported Devices

--device ANE    # Apple Neural Engine (fastest, default)
--device CPU    # CPU only
--device GPU    # CPU + GPU
--device ALL    # All available compute units

Output

JSON with detected text regions, confidence scores, and bounding quads:

{
  "images": [{
    "region_count": 38,
    "latency_ms": 359.2,
    "regions": [
      {"text": "Council", "confidence": 0.48, "quad": {"points": [...]}},
      {"text": "BANK STATEMENT", "confidence": 0.55, "quad": {"points": [...]}}
    ]
  }]
}

File Structure

v2_english/
  manifest.json                        # Model metadata + ANE optimization config
  charset.txt                          # Character vocabulary (JSON array)
  v2_english_detector.mlmodel          # RegNet-X-8GF detector (~181 MB)
  v2_english_recognizer.mlpackage/     # Transformer recognizer
  v2_english_relational.mlpackage/     # GNN relational model

v2_multilingual/
  manifest.json
  charset.txt
  v2_multilingual_detector.mlmodel
  v2_multilingual_recognizer.mlpackage/
  v2_multilingual_relational.mlpackage/

ANE Optimization Details

From manifest.json:

Detector: NCHW input layout, 1024×1024 fixed resolution, float32
Recognizer: NCHW input layout, batch size 16, float16
Relational: Max 256 regions, float16
Host pipeline: Preprocessing, NMS, quad rectification, and batching run on CPU

Swift Package: mweinbach/SwiftNemotronOCR — Full Swift implementation with CoreML + MLX backends
MLX Weights: mweinbach/nemotron-ocr-v2-mlx — MLX-format weights for CPU/GPU inference
Original Model: nvidia/nemotron-ocr-v2 — NVIDIA's original PyTorch release

License

This model inherits the NVIDIA Open Model License from the original Nemotron OCR v2 release.

Sources

1 source

Hugging FacePrimaryVersion 3f48f92186b307341c4727a9281ca5cc33eefef8

huggingface.co/mweinbach/nemotron-ocr-v2-coreml/tree/3f48f92186b307341c4727a9281ca5cc33eefef8

Verified Nov 5

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

8 artifacts

v2_english/v2_english_recognizer.mlpackage/Data/com.apple.CoreML/weights/._weight.bin

bin · 4.00 KB · SHA-256 09c63151f197…72f7 · Hugging Face

Download file

v2_english/v2_english_recognizer.mlpackage/Data/com.apple.CoreML/weights/weight.bin

bin · 11.7 MB · SHA-256 625d810a7930…8deb · Hugging Face

Download file

v2_english/v2_english_relational.mlpackage/Data/com.apple.CoreML/weights/._weight.bin

bin · 4.00 KB · SHA-256 09c63151f197…72f7 · Hugging Face

Download file

v2_english/v2_english_relational.mlpackage/Data/com.apple.CoreML/weights/weight.bin

bin · 4.49 MB · SHA-256 b434adf80dbb…5c95 · Hugging Face

Download file

v2_multilingual/v2_multilingual_recognizer.mlpackage/Data/com.apple.CoreML/weights/._weight.bin

bin · 4.00 KB · SHA-256 09c63151f197…72f7 · Hugging Face

Download file

v2_multilingual/v2_multilingual_recognizer.mlpackage/Data/com.apple.CoreML/weights/weight.bin

bin · 68.9 MB · SHA-256 719b71d81719…d2dd · Hugging Face

Download file

v2_multilingual/v2_multilingual_relational.mlpackage/Data/com.apple.CoreML/weights/._weight.bin

bin · 4.00 KB · SHA-256 09c63151f197…72f7 · Hugging Face

Download file

v2_multilingual/v2_multilingual_relational.mlpackage/Data/com.apple.CoreML/weights/weight.bin

bin · 4.56 MB · SHA-256 86a0e79a3eeb…db35 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeAug 27huggingface.co/mweinbach/nemotron-ocr-v2-coreml

--- license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ library_name: coreml tags: - coreml - ocr - apple-silicon - swift - nemotron - nvidia - apple-neural-engine - ane - document-understanding - text-recognition pipeline_tag: image-to-text base_model: nvidia/nemotron-ocr-v2 --- # Nemotron OCR v2 — CoreML (Apple Neural Engine) CoreML-format models for [NVIDIA Nemotron OCR v2](https://huggingface.co/nvidia/nemotron-ocr-v2), exported for native Apple Silicon inference targeting the Apple Neural Engine (ANE). ## Model Details Three-stage OCR pipeline optimized for ANE acceleration: | Component | Format | Precision | Size | |-----------|--------|-----------|------| | **Detector** | `.mlmodel` | float32 | ~181 MB | | **Recognizer** | `.mlpackage` | float16 | ~12–72 MB | | **Relational** | `.mlpackage` | float16 | ~5 MB | ### Variants | Variant | Charset | Detector Resolution | Batch Size | |---------|---------|-------------------|------------| | `v2_english` | 855 characters | 1024×1024 | 16 regions | | `v2_multilingual` | ~42K characters | 1024×1024 | 16 regions | ### ANE Performance On Apple Silicon, the CoreML ANE path provides the lowest latency: | Backend | Typical Latency | Device | |---------|----------------|--------| | **CoreML ANE** | **~350ms** | Apple Neural Engine | | MLX GPU | ~2800ms | Metal GPU | | MLX CPU | ~6700ms | CPU | ## Usage with SwiftNemotronOCR This model is designed for use with [SwiftNemotronOCR](https://github.com/mweinbach/SwiftNemotronOCR), an all-Swift OCR pipeline. ### Quick Start ```bash # Clone the Swift package git clone https://github.com/mweinbach/SwiftNemotronOCR.git cd SwiftNemotronOCR # Build swift build -c release # Download this model # Place v2_english/ and/or v2_multilingual/ under a model/coreml/ directory # Run OCR on ANE .build/release/apple-ocr-runner \ --runtime coreml \ --device ANE \ --model-dir /path/to/model/coreml \ --image /path/to/image.png \ --variant en \ --level paragraph ``` ### Supported Devices ```bash --device ANE # Apple Neural Engine (fastest, default) --device CPU # CPU only --device GPU # CPU + GPU --device ALL # All available compute units ``` ### Output JSON with detected text regions, confidence scores, and bounding quads: ```json { "images": [{ "r...

NoteNov 5huggingface.co/mweinbach/nemotron-ocr-v2-coreml

Source context: 76 downloads · 0 likes · Pipeline image-to-text · Library coreml · Repo mweinbach/nemotron-ocr-v2-coreml

NoteAug 27huggingface.co/mweinbach/nemotron-ocr-v2-coreml

Source context: 58 downloads · 0 likes · Pipeline image-to-text · Library coreml · Repo mweinbach/nemotron-ocr-v2-coreml

Nemotron Ocr v2 Coreml

Nemotron OCR v2 — CoreML (Apple Neural Engine)

Model Details

Variants

ANE Performance

Usage with SwiftNemotronOCR

Quick Start

Supported Devices

Output

File Structure

ANE Optimization Details

Related

License

Download files