| Parameter | Value |
|---|---|
| Encoder layers | 4 |
| Decoder layers | 1 |
| Hidden dim | 256 |
| FFN dim | 1024 |
| Vocabulary | 16k joint SentencePiece |
| Quantization | intgemm8 (int8) |
| Model size | ~15–20MB |
| Peak RAM (inference) | ~50–80MB |
| File | Description |
|---|---|
model.intgemm8.bin | Quantized Marian model (deploy this) |
vocab.cy.spm | Welsh SentencePiece vocabulary |
vocab.en.spm | English SentencePiece vocabulary |
1marian-decoder \
2 -m model.intgemm8.bin \
3 -v vocab.cy.spm vocab.en.spm \
4 --cpu-threads 4 \
5 --beam-size 1