source languages: nl; target languages: en; OPUS readme: nl-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
Open-weight model · Translation
nllb-rus-tyv-v3-mlx-q4
by Ali Kuzhuget Agisight/nllb-rus-tyv-v3-mlx-q4
nllb-rus-tyv-v3-mlx-q4 is an open-weight model for translation from Ali Kuzhuget, released under Creative Commons Attribution-NonCommercial 4.0. It has 1,024-token context. Its published files total 234.8 MB.
MLX port of Agisight/nllb-rus-tyv-v3-dict16.5k, a Russian ↔ Tuvan translation model fine-tuned from Meta's NLLB-200-distilled-600M with a vocabulary pruned to 16.5K tokens. Runs fully offline on Apple Silicon (Mac, iPhone, iPad) via MLX.
Parameters—
Context1,024
Weights232.6 MB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads—
Model Card
MLX port of Agisight/nllb-rus-tyv-v3-dict16.5k, a Russian ↔ Tuvan translation model fine-tuned from Meta's NLLB-200-distilled-600M with a vocabulary pruned to 16.5K tokens. Runs fully offline on Apple Silicon (Mac, iPhone, iPad) via MLX. mlx-lm does not support encoder-decoder models, so the M2M100 architecture is re-implemented in nllbmlx.py (included), with a KV cache for fast greedy decoding. The float32 port reproduces the PyTorch model exactly: 100/100 identical translations on a spot check and identical chrF++/BLEU on the full clean test set. Clean test set: held-out test split of Agisight/tyv-rus-200k used for NLLB v3 (shuffle(seed=42), pairs 2000–4000), with pairs whose Tuvan or…
Excerpt from the card by Ali Kuzhuget, licensed cc-by-nc-4.0.
Configuration
- Architecture
- M2M100ForConditionalGeneration
- Context length (tokens)
- 1,024
- Layers
- 12
- Vocabulary size
- 16,722
- Stored precision
- float32
- Model type
- m2m_100
Identity and Version
- Repository
- Agisight/nllb-rus-tyv-v3-mlx-q4
- Publisher
- Ali Kuzhuget
- Task
- Translation
- Modality
- Text
- Library
- mlx
- Parameters
- Not stated by the source
- Languages
- ru, tyv
- Revision
- 406ce023ce2264f2b2c929b32957431a3e0437e7
- First published
- 2026-09-30
- Last updated
- 2026-10-01
Files and Weights
7 files, 234.8 MB in total. The weights are 1 file totalling 232.6 MB in safetensors.
Weights1 file · 232.6 MB
Configuration2 files · 9.7 KB
Tokenizer2 files · 2.2 MB
Documentation1 file · 3.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| weights.safetensors | Weights | 232.6 MB | 7b2294335141 |
| config.json | Configuration | 1.0 KB | — |
| nllb_mlx.py | Configuration | 8.7 KB | — |
| README.md | Documentation | 3.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 2.2 MB | — |
| tokenizer_config.json | Tokenizer | 717 B | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 232.6 MB
Download from Ali Kuzhuget
Released by Ali Kuzhuget through its official repository on Hugging Face. Read the license.
Built From
- Derived from Agisight/nllb-rus-tyv-v3-dict_16.5k
- Trained on (disclosed) Agisight/tyv-rus-200k
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 232.6 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About nllb-rus-tyv-v3-mlx-q4
Can I use nllb-rus-tyv-v3-mlx-q4 commercially?
Not without separate permission. nllb-rus-tyv-v3-mlx-q4 is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
What is nllb-rus-tyv-v3-mlx-q4's context length?
1,024 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This is the model card of NLLB-200's distilled 600M variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
source languages: en; target languages: ru; OPUS readme: en-ru; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.
This model can be used for translation and text-to-text generation. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Further details about the dataset for this model can be found in the OPUS readme: en-de
hfname: kor-eng - sourcelanguages: kor - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'korHani', 'korHang', 'korLatn', 'kor'} - tgtconstituents: {'eng'} - srcmultilingual: False - tgtmultilingual: False - urlmodel: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.zip - urltestset: https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opus-2020-06-17.test.txt - srcalpha3: kor - tgtalpha3: eng - shortpair: ko-en - chrF2score: 0.588 - brevitypenalty: 0.9590000000000001 - reflen: 17711.0 - srcname: Korean - tgtname: English - traindate…
source languages: de; target languages: en; OPUS readme: de-en; dataset: opus; model: transformer-align; pre-processing: normalization + SentencePiece.