MiniCPM Paper | GitHub Repo | 中文 | UltraData | MiniCPM Desk Pet
## Highlights We are releasing **MiniCPM5-1B**, the first model in the **MiniCPM5** series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA on the benchmark suite. 🏆 **1B-class open-source SOTA**: compared with strong open-source models in the same size class, MiniCPM5-1B reaches SOTA within this comparison set. Its advantage is most visible in agentic tool use, code generation, and difficult reasoning.  🧠 **Dual Mode Reasoning**: built-in `
**Project repo**: [OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)
## Model List
Use this directory to choose the model format that matches your runtime:
- **[MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B) · BF16 final release (post-trained with RL + OPD) **👈 you are here**
- **[MiniCPM5-1B-SFT](https://huggingface.co/openbmb/MiniCPM5-1B-SFT)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-SFT) · BF16 SFT-only checkpoint (before RL / OPD)
- **[MiniCPM5-1B-Base](https://huggingface.co/openbmb/MiniCPM5-1B-Base)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-Base) · BF16 base checkpoint (pre-training only)
- **[MiniCPM5-1B-GGUF](https://huggingface.co/openbmb/MiniCPM5-1B-GGUF)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-GGUF) · GGUF for llama.cpp / Ollama / LM Studio
- **[MiniCPM5-1B-MLX](https://huggingface.co/openbmb/MiniCPM5-1B-MLX)** · [ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B-MLX) · MLX / 4bit for Apple Silicon
## Model Information
MiniCPM5-1B has the following features:
- **Type**: Causal Language Model
- **Architecture**: Standard `LlamaForCausalLM`
- **Number of Parameters**: 1,080,632,832
- **Number of Non-Embedding Parameters**: 679,552,512
- **Number of Layers**: 24
- **Number of Attention Heads (GQA)**: 16 for Q and 2 for KV
- **Context Length**: 131,072
## Introduction
MiniCPM5-1B is the first checkpoint in the MiniCPM5 series. It is designed for local assistants, coding agents, tool-use workflows, and reasoning scenarios where a compact model is preferred. The model keeps a small deployment footprint while providing native long-context support and both Think / No Think chat modes through the same checkpoint.
## Evaluation Results
We compare MiniCPM5-1B with strong open-source models in the same size class, including **LFM2.5-1.2B-Thinking**, **Qwen3-0.6B/think** and **Qwen3.5-0.8B/think**. These are capable baselines; within this comparison set, MiniCPM5-1B reaches 1B-class open-source SOTA, with its advantage most visible in tool use, code generation, and difficult reasoning. This makes it a practical choice for local coding agents, tool assistants, and reasoning assistants.
## Training Recipe
The training of MiniCPM5-1B is a full-stack practice of **[UltraData Tiered Data Management](https://arxiv.org/pdf/2602.09003)**, covering three stages: base training, mid-training, and post-training.
During **base training**, the model goes through stable training and decay training to build core language capability and training stability. It then enters **mid-training** to further strengthen target capabilities and adapt to the target data distribution. The training corpus is released alongside the model as [Ultra-FineWeb](https://huggingface.co/datasets/openbmb/Ultra-FineWeb), [Ultra-FineWeb-L3](https://huggingface.co/datasets/openbmb/Ultra-FineWeb-L3), and [UltraData-Math](https://huggingface.co/datasets/openbmb/UltraData-Math).
During **post-training**, we proceed in three steps: **SFT**, **RL**, and **OPD**. We first use **200B tokens of deep-thinking SFT** and **200B tokens of hybrid-thinking SFT** to establish deep-thinking, hybrid-thinking, and general chat abilities; the SFT data is released as [UltraData-SFT-2605](https://huggingface.co/datasets/openbmb/UltraData-SFT-2605). We then train specialized **RL teachers** for math, code, closed-book QA, writing, and related domains, and use **On-Policy Distillation (OPD)** to distill these teachers back into one release model.
### What does RL + OPD bring?
**RL + OPD** is a key part of MiniCPM5-1B post-training. On math, code and instruction-following tasks, RL + OPD raises the average score by **↑16 points** while cutting the share of responses that hit the max-tokens budget by **↓29 percentage points**. The figures below show the two-stage Reasoning RL pipeline, score gains, and the drop in overlong responses.
**RL** combines complementary training signals for reasoning, closed-book QA, writing, instruction following, long-context understanding, and general dialogue. Reasoning RL is based on [DAPO-Math-17k](https://huggingface.co/datasets/BytedTsinghua-SIA/DAPO-Math-17k) and uses a two-stage length schedule to reduce overlong responses while improving reasoning accuracy. We also use [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa), [NQ-Open](https://huggingface.co/datasets/google-research-datasets/nq_open), [LongWriter-Zero-RLData](https://huggingface.co/datasets/THU-KEG/LongWriter-Zero-RLData), synthesized verifiable RLVR data, and pair-wise RLHF signals to improve reliability, instruction following, and user experience.
**OPD** builds on Thinking Machines Lab's [On-Policy Distillation](https://thinkingmachines.ai/blog/on-policy-distillation/) and incorporates implementation improvements from [Rethinking On-Policy Distillation](https://arxiv.org/pdf/2604.13016). In the RL framework, we use reverse KL divergence as the advantage estimate, replacing the original verification-based advantage. At each response position, we take top-k logits from both the student and teacher models, compute reverse KL on the union of the two token sets, and balance the accuracy of the RKL signal with training efficiency. OPD reuses the in-domain prompts used to train each RL teacher as distillation data, so no additional data curation is required.
## Quickstart
### vLLM
```bash
pip install "vllm>=0.21"
vllm serve openbmb/MiniCPM5-1B --port 8000
```
```bash
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openbmb/MiniCPM5-1B",
"messages": [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}],
"max_tokens": 128,
"temperature": 0.7
}'
```
### SGLang
```bash
pip install "sglang[srt]>=0.5.12"
python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000
```
```bash
curl http://localhost:30000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openbmb/MiniCPM5-1B",
"messages": [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}],
"max_tokens": 128,
"temperature": 0.7
}'
```
### Transformers
```bash
pip install -U "transformers>=5.6" accelerate torch
```
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "openbmb/MiniCPM5-1B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
messages = [{"role": "user", "content": "Who are you? Please briefly introduce yourself."}]
inputs = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
enable_thinking=False,
return_tensors="pt",
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
```
Recommended chat template sampling:
| Mode | Recommended params | Enable |
| --- | --- | --- |
| **Think** | `temperature=0.9, top_p=0.95` | `enable_thinking=True` |
| **No Think** | `temperature=0.7, top_p=0.95` | `enable_thinking=False` |
## Tool Calling
For tool / function calling, **SGLang is the recommended backend**. MiniCPM5-1B emits XML-style tool calls and SGLang's built-in `minicpm5` parser converts them to OpenAI-compatible `tool_calls` natively:
```bash
python -m sglang.launch_server --model-path openbmb/MiniCPM5-1B --port 30000 \
--tool-call-parser minicpm5 # or: --tool-call-parser auto
```
## GitHub Cookbooks and Agent Skills
MiniCPM5-1B uses the **standard `LlamaForCausalLM` architecture**, so mainstream inference engines can load it directly: **no custom kernels, no model-code fork**. For step-by-step deployment and fine-tuning instructions, use the GitHub cookbooks below. Agent Skills are linked as GitHub resources for users working with Cursor / Claude Code style coding agents.
### Deployment
| Backend | Model format / use case | Cookbook | Agent Skill |
| --- | --- | --- | --- |
| Transformers | BF16 / FP16 local Python inference, GPU + CPU | [transformers.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/transformers.md) | [minicpm5-deploy-transformers](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-transformers/SKILL.md) |
| vLLM | BF16 / FP16 OpenAI server | [vllm.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/vllm.md) | [minicpm5-deploy-vllm](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-vllm/SKILL.md) |
| SGLang | BF16 / FP16 OpenAI server, recommended for tool calling | [sglang.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/sglang.md) | [minicpm5-deploy-sglang](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-sglang/SKILL.md) |
| llama.cpp | GGUF local inference, CPU/GPU | [llama_cpp.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/llama_cpp.md) | [minicpm5-deploy-llama-cpp](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-llama-cpp/SKILL.md) |
| Ollama | GGUF local on-device runtime | [ollama.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/ollama.md) | [minicpm5-deploy-ollama](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-ollama/SKILL.md) |
| LM Studio | GGUF Mac desktop app and OpenAI server | [lmstudio.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/lmstudio.md) | [minicpm5-deploy-lmstudio](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-lmstudio/SKILL.md) |
| MLX | MLX / 4bit local inference on Apple Silicon | [mlx.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/deployment/mlx.md) | [minicpm5-deploy-mlx](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-deploy-mlx/SKILL.md) |
### Fine-tuning
| Framework | Use case | Cookbook | Agent Skill |
| --- | --- | --- | --- |
| TRL + PEFT | LoRA / SFT fine-tuning | [trl.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/finetune/trl.md) | [minicpm5-finetune-trl](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-finetune-trl/SKILL.md) |
| LLaMA-Factory | Fine-tuning | [llamafactory.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/finetune/llamafactory.md) | [minicpm5-finetune-llamafactory](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-finetune-llamafactory/SKILL.md) |
| ms-swift | Fine-tuning | [ms_swift.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/finetune/ms_swift.md) | [minicpm5-finetune-ms-swift](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-finetune-ms-swift/SKILL.md) |
| unsloth | Fine-tuning | [unsloth.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/finetune/unsloth.md) | [minicpm5-finetune-unsloth](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-finetune-unsloth/SKILL.md) |
| xtuner | Fine-tuning | [xtuner.md](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/docs/finetune/xtuner.md) | [minicpm5-finetune-xtuner](https://github.com/OpenBMB/MiniCPM/blob/minicpm5/skills/minicpm5-finetune-xtuner/SKILL.md) |
## Desktop Pet
We also ship **[OpenBMB/MiniCPM-Desk-Pet](https://github.com/OpenBMB/MiniCPM-Desk-Pet)**, a desktop pet driven locally by MiniCPM5-1B. It supports Apple Silicon / NVIDIA GPU / CPU paths, can work with coding agents such as Cursor, Claude Code, and Codex, and supports LoRA persona switching.
## Limitations and Responsible Use
MiniCPM5-1B is a language model that generates content based on learned statistical patterns from training data. It may produce inaccurate, biased, or unsafe outputs, and generated content should be reviewed and verified before use in high-stakes settings.
Users are responsible for evaluating outputs, applying appropriate safeguards, and complying with applicable laws, regulations, and platform policies.
## License
This repository and MiniCPM model weights are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
## Citation
Please cite our paper if you find our work valuable:
```bibtex
@article{minicpm4,
title={Minicpm4: Ultra-efficient llms on end devices},
author={MiniCPM, Team},
journal={arXiv preprint arXiv:2506.07900},
year={2025}
}
```