Metraipolis › archive › dc_28ae510b29bc
MNN-Pocket-0.3B Technical Report — arXiv:2611.12311
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12311
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:49.534Z
- SHA-256 of the archived text
2d96537bef3d9d27d7f9bb9948bc5391bd022c81128bfc35c78ce505d68c7806- Stable URL of this page
https://metraipolis.com/documento/dc_28ae510b29bc
How to cite
MNN-Pocket-0.3B Technical Report — arXiv:2611.12311 — arXiv (en), https://arxiv.org/abs/2611.12311 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28ae510b29bc (Metraipolis archive dc_28ae510b29bc, sha256 2d96537bef3d9d27d7f9bb9948bc5391bd022c81128bfc35c78ce505d68c7806)
BibTeX
@misc{dc28ae510b29bc,
title = {MNN-Pocket-0.3B Technical Report — arXiv:2611.12311},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12311},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28ae510b29bc; sha256 2d96537bef3d9d27d7f9bb9948bc5391bd022c81128bfc35c78ce505d68c7806},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12311. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This technical report presents MNN-Pocket-0.3B, a compact 300M-parameter dense language model designed for efficient on-device deployment and supporting context lengths of up to 32K tokens. With an INT4 deployment footprint of only 173 MB and decoding throughput of up to 466 tokens/s on iPad Pro M5 (Metal), it can be seamlessly integrated into applications on edge devices such as smartphones and smart glasses. MNN-Pocket-0.3B is developed through the co-design of its architecture, data, training pipeline, and inference system. Hardware-aware architecture selection and dependency-aware vocabulary pruning balance model capability with on-device memory and compute constraints. A four-stage pre-training pipeline covering approximately 4.1 trillion high-quality Chinese and English tokens equips the model with broad knowledge and reasoning capabilities. This is followed by a three-stage post-training pipeline comprising instruction fine-tuning, multi-teacher on-policy distillation, and quantization-aware training. Finally, hardware-specific optimizations in the MNN inference engine enable fast, memory-efficient inference and long-context processing. Extensive evaluations demonstrate that MNN-Pocket-0.3B achieves frontier-level performance among models of comparable size, with particularly strong results in Chinese and English knowledge and reasoning, mathematics, coding, and instruction following. It consistently outperforms similarly sized open-source models and even surpasses several 0.5B-parameter models on instruction-following benchmarks. We release MNN-Pocket-0.3B with open weights and ready-to-use MNN deployment packages. We hope it will provide a practical foundation for capable, responsive, and memory-efficient edge applications while advancing research and development in on-device language models. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.12311 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:52.453Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).