---
license: apache-2.0
language:
- zh
- en
pipeline_tag: text-generation
library_name: transformers
---
GitHub Repo |
Technical Report
👋 Join us on Discord and WeChat
## What's New
- [2025.06.06] **MiniCPM4** series are released! This model achieves ultimate efficiency improvements while maintaining optimal performance at the same scale! It can achieve over 5x generation acceleration on typical end-side chips! You can find technical report on [arXiv]().🔥🔥🔥
## MiniCPM4 Series
- [MiniCPM4-0.5B](https://huggingface.co/openbmb/MiniCPM4-0.5B): TODO
- [MiniCPM4-8B](https://huggingface.co/openbmb/MiniCPM4-8B): TODO **<-- you are here**
- [MiniCPM4-8B-Eagle-FRSpec](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec)
- [MiniCPM4-8B-Eagle-FRSpec-QAT](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT)
- [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): TODO
- [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): TODO
- [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): TODO
- [MiniCPM4-MCP](https://huggingface.co/openbmb/MiniCPM4-MCP): TODO
## Introduction
MiniCPM 4 is an extremely efficient edge-side large model that has undergone efficient optimization across four dimensions: model architecture, learning algorithms, training data, and inference systems, achieving ultimate efficiency improvements.
- 🏗️ **Efficient Model Architecture:**
- InfLLM v2 -- Trainable Sparse Attention Mechanism: Adopts a trainable sparse attention mechanism architecture where each token only needs to compute relevance with less than 5% of tokens in 128K long text processing, significantly reducing computational overhead for long texts
- 🧠 **Efficient Learning Algorithms:**
- Model Wind Tunnel 2.0 -- Efficient Predictable Scaling: Introduces scaling prediction methods for performance of downstream tasks, enabling more precise model training configuration search
- BitCPM -- Ultimate Ternary Quantization: Compresses model parameter bit-width to 3 values, achieving 90% extreme model bit-width reduction
- Efficient Training Engineering Optimization: Adopts FP8 low-precision computing technology combined with Multi-token Prediction training strategy
- 📚 **High-Quality Training Data:**
- UltraClean -- High-quality Pre-training Data Filtering and Generation: Builds iterative data cleaning strategies based on efficient data verification, open-sourcing high-quality Chinese and English pre-training dataset [UltraFinweb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb)
- UltraChat v2 -- High-quality Supervised Fine-tuning Data Generation: Constructs large-scale high-quality supervised fine-tuning datasets covering multiple dimensions including knowledge-intensive data, reasoning-intensive data, instruction-following data, long text understanding data, and tool calling data
- ⚡ **Efficient Inference System:**
- FRSpec -- Lightweight Speculative Sampling: Achieves draft model acceleration through vocabulary pruning of draft model
- ArkInfer -- Cross-platform Deployment System: Supports efficient deployment across multiple backend environments, providing flexible cross-platform adaptation capabilities
## Usage
### Inference with Transformers
### Inference with [vLLM](https://github.com/vllm-project/vllm)
## Evaluation Results
On two typical end-side chips, Jetson AGX Orin and RTX 4090, MiniCPM4 demonstrates significantly faster processing speed compared to similar-size models in long text processing tasks. As text length increases, MiniCPM4's efficiency advantage becomes more pronounced. On the Jetson AGX Orin platform, compared to Qwen3-8B, MiniCPM4 achieves approximately 7x decoding speed improvement.
#### Comprehensive Evaluation
MiniCPM4 launches end-side versions with 8B and 0.5B parameter scales, both achieving best-in-class performance in their respective categories.
#### Long Text Evaluation
MiniCPM4 is pre-trained on 32K long texts and achieves length extension through YaRN technology. In the 128K long text needle-in-a-haystack task, MiniCPM4 demonstrates outstanding performance.
## Statement
- As a language model, MiniCPM generates content by learning from a vast amount of text.
- However, it does not possess the ability to comprehend or express personal opinions or value judgments.
- Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers.
- Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.
## LICENSE
- This repository is released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
- The usage of MiniCPM model weights must strictly follow [MiniCPM Model License](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md).
- The models and weights of MiniCPM are completely free for academic research. after filling out a [questionnaire](https://modelbest.feishu.cn/share/base/form/shrcnpV5ZT9EJ6xYjh3Kx0J6v8g) for registration, are also available for free commercial use.
## Citation
- Please cite our [paper](TODO) if you find our work valuable.
```bibtex
TODO
```
