# MNN-Pocket-0.3B Technical Report

**Authors:** MNN Team  
**Published:** 9 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.12311) · [PDF](https://arxiv.org/pdf/2611.12311) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.12311.html)

## Key numbers

- **32K**: …language model designed for efficient on-device deployment and supporting context lengths of up to 32K tokens.
- **466**: …of only 173 MB and decoding throughput of up to 466 tokens/s on iPad Pro M5

## Abstract

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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.