---
license: cc-by-nc-4.0
language:
  - multilingual
library_name: coreml
pipeline_tag: translation
base_model: facebook/nllb-200-distilled-600M
tags:
  - coreml
  - translation
  - nllb
  - on-device
  - apple-silicon
  - neural-engine
  - m2m100
  - palettization
  - quantized
---

# NLLB-200 distilled 600M — Core ML (seq 256, ANE, palettized / pal8)

Core ML `.mlpackage` bundles for **encoder** and **KV-cache decoder** (`init` + `step`), exported from [`facebook/nllb-200-distilled-600M`](https://huggingface.co/facebook/nllb-200-distilled-600M). Fixed **sequence length 256**, **8-bit palettization (pal8)** on weights for a smaller footprint and Apple Neural Engine–friendly deployment.

## Contents

| Artifact | Role |
|----------|------|
| `NLLB_Encoder_256.mlpackage` | Encode source tokens |
| `NLLB_Decoder_256_init.mlpackage` | Decoder first step (no past KV) |
| `NLLB_Decoder_256_step.mlpackage` | Autoregressive step with past KV |
| `config.json` | Architecture metadata (`seq_len`, `compute_units`, etc.) |
| `tokenizer/` | Reference tokenizer files for the app pipeline |

## Companion variant

- **Float32 weights** (no palettization): [`aoiandroid/nllb200-coreml-256-ane`](https://huggingface.co/aoiandroid/nllb200-coreml-256-ane)

## Config highlights (`config.json`)

- `model_type`: `m2m_100` / `M2M100ForConditionalGeneration`
- `seq_len`: **256**
- `ane_optimized`: **true**
- `compute_units`: **CPU_AND_NE**
- Weights in the `.mlpackage` bundles use **pal8** palettization (see Hub file sizes vs the float32 repo).

## Base model and license

- Source weights: **NLLB-200 distilled 600M** (Meta / FAIR).  
- Original terms are **CC-BY-NC 4.0**. This repository only ships a **derived Core ML export** for on-device use; the same license restrictions apply.

## Intended use

- **macOS / iOS** on-device translation via `MLModel` (or `coremltools` in Python for validation).
- Language direction is controlled in your app: tokenizer `src_lang`, forced target BOS (e.g. `eng_Latn`), and your beam/greedy loop around `Decoder_256_step`.
- Compare **accuracy and latency** against the float32 sibling on your devices; palettization can change numerical behavior.

## Limitations

- Fixed **max sequence length 256** at export time; longer inputs require truncation or a different export.
- Not a drop-in Hugging Face `transformers` checkpoint; this is a **split Core ML deployment** (encoder + decoder packages).

## Maintainer

[`aoiandroid`](https://huggingface.co/aoiandroid)