Instructions to use openbmb/MiniCPM4-8B-Eagle-FRSpec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM4-8B-Eagle-FRSpec with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openbmb/MiniCPM4-8B-Eagle-FRSpec", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM4-8B-Eagle-FRSpec", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM4-8B-Eagle-FRSpec with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM4-8B-Eagle-FRSpec"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-8B-Eagle-FRSpec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM4-8B-Eagle-FRSpec

SGLang

How to use openbmb/MiniCPM4-8B-Eagle-FRSpec with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "openbmb/MiniCPM4-8B-Eagle-FRSpec" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-8B-Eagle-FRSpec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "openbmb/MiniCPM4-8B-Eagle-FRSpec" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openbmb/MiniCPM4-8B-Eagle-FRSpec",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM4-8B-Eagle-FRSpec with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM4-8B-Eagle-FRSpec
```

BigDong commited on Jun 6, 2025

Commit

f26e9d7

1 Parent(s): 4dfba7c

update README.md

Browse files

Files changed (1) hide show

README.md +35 -10

README.md CHANGED Viewed

@@ -12,15 +12,14 @@ library_name: transformers
 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
-<a href="TODO" target="_blank">Technical Report</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 </p>
 ## 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](TODO).🔥🔥🔥
 ## MiniCPM4 Series
 MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
@@ -31,7 +30,32 @@ MiniCPM4 series are highly efficient large language models (LLMs) designed expli
 - [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
 - [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
 - [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers.
-- [MiniCPM4-MCP](https://huggingface.co/openbmb/MiniCPM4-MCP): Based on MiniCPM4-8B, accepts users' queries and available MCP tools as input and autonomously calls relevant MCP tools to satisfy user requirements.
 ## Statement
 - As a language model, MiniCPM generates content by learning from a vast amount of text.
@@ -40,14 +64,15 @@ MiniCPM4 series are highly efficient large language models (LLMs) designed expli
 - 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
 ```

 <p align="center">
 <a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
+<a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a>
 </p>
 <p align="center">
 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
 </p>
 ## 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 [here](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf).🔥🔥🔥
 ## MiniCPM4 Series
 MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
 - [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
 - [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width.
 - [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers.
+- [MiniCPM4-MCP](https://huggingface.co/openbmb/MiniCPM4-MCP): Based on MiniCPM4-8B, accepts users' queries and available MCP tools as input and autonomously calls relevant MCP tools to satisfy users' requirements.
+## Introduction
+MiniCPM4-8B-Eagle-FRSpec is a Eagle model trained with MiniCPM4-8B. It clould be apply on our inference framework [cpm.cu](https://github.com/xxx) with FRSpec,  accelerating the generation speed by 7 times compared to Qwen3-8B.
+## Usage
+### Inference with cpm.cu
+```
+# case 1: verify model is fp16 or bf16
+cd cpm.cu/tests
+python3 test_generate.py \
+    --no-apply-quant \
+    --no-apply-eagle-quant
+# case 2: verify model is quanted with Marlin (W4A16, group size = 128)
+cd cpm.cu/tests
+python3 test_generate.py \
+    --apply-quant \
+    --no-apply-eagle-quant
+```
+## Evaluation
+Tested on two representative edge devices, the Jetson AGX Orin and RTX 4090, MiniCPM4 with MiniCPM4-8B-Eagle-FRSpec demonstrates significantly superior processing speed over models of comparable size for long-text processing tasks. Its performance advantage becomes increasingly pronounced as the text length increases. On the Jetson AGX Orin platform, MiniCPM4 achieves approximately a 7x improvement in generation speed compared to Qwen3-8B.
+![speed test](https://raw.githubusercontent.com/OpenBMB/MiniCPM/refs/heads/minicpm-4/assets/minicpm4/efficiency.png)
 ## Statement
 - As a language model, MiniCPM generates content by learning from a vast amount of text.
 - Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own.
 ## LICENSE
+- This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
 ## Citation
+- Please cite our [paper](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf) if you find our work valuable.
 ```bibtex
+@article{minicpm4,
+  title={{MiniCPM4}: Ultra-Efficient LLMs on End Devices},
+  author={MiniCPM Team},
+  year={2025}
+}
 ```