Instructions to use openbmb/MiniCPM-V-4_5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-V-4_5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="openbmb/MiniCPM-V-4_5", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("openbmb/MiniCPM-V-4_5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openbmb/MiniCPM-V-4_5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/MiniCPM-V-4_5"
# 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/MiniCPM-V-4_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/openbmb/MiniCPM-V-4_5

SGLang

How to use openbmb/MiniCPM-V-4_5 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/MiniCPM-V-4_5" \
    --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/MiniCPM-V-4_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/MiniCPM-V-4_5" \
        --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/MiniCPM-V-4_5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use openbmb/MiniCPM-V-4_5 with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-4_5
```

yuzaa commited on Aug 29, 2025

Commit

a426d2a

verified ·

1 Parent(s): d272cfd

Update README.md

Browse files

Files changed (1) hide show

README.md +77 -0

README.md CHANGED Viewed

@@ -60,6 +60,83 @@ MiniCPM-V 4.5 can be easily used in various ways: (1) [llama.cpp](https://github
 <img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpmv_4_5_evaluation_result.png" , width=100%>
 </div>
 ### Examples
 <div align="center">

 <img src="https://raw.githubusercontent.com/openbmb/MiniCPM-o/main/assets/minicpmv_4_5_evaluation_result.png" , width=100%>
 </div>
+### Inference Efficiency
+**OpenCompass**
+<div align="left">
+<table style="margin: 0px auto;">
+    <thead>
+            <tr>
+              <th align="left">Model</th>
+              <th>Size</th>
+              <th>Avg Score ↑</th>
+              <th>Total Inference Time ↓</th>
+            </tr>
+    </thead>
+    <tbody align="center">
+        <tr>
+            <td nowrap="nowrap" align="left">GLM-4.1V-9B-Thinking</td>
+            <td>10.3B</td>
+            <td>76.6</td>
+            <td>17.5h</td>
+        </tr>
+        <tr>
+            <td nowrap="nowrap" align="left">MiMo-VL-7B-RL</td>
+            <td>8.3B</td>
+            <td>76.4</td>
+            <td>11h</td>
+        </tr>
+        <tr>
+            <td nowrap="nowrap" align="left">MiniCPM-V 4.5</td>
+            <td>8.7B</td>
+            <td>77.0</td>
+            <td>7.5h</td>
+        </tr>
+    </tbody>
+</table>
+</div>
+**Video-MME**
+<div align="left">
+<table style="margin: 0px auto;">
+    <thead>
+          <tr>
+              <th align="left">Model</th>
+              <th>Size</th>
+              <th>Avg Score ↑</th>
+              <th>Total Inference Time ↓</th>
+              <th>GPU Mem ↓</th>
+          </tr>
+    </thead>
+    <tbody align="center">
+          <tr>
+              <td nowrap="nowrap" align="left">Qwen2.5-VL-7B-Instruct</td>
+              <td>8.3B</td>
+              <td>71.6</td>
+              <td>3h</td>
+              <td>60G</td>
+          </tr>
+          <tr>
+              <td nowrap="nowrap" align="left">GLM-4.1V-9B-Thinking</td>
+              <td>10.3B</td>
+              <td>73.6</td>
+              <td>2.63h</td>
+              <td>32G</td>
+          </tr>
+          <tr>
+              <td nowrap="nowrap" align="left">MiniCPM-V 4.5</td>
+              <td>8.7B</td>
+              <td>73.5</td>
+              <td>0.26h</td>
+              <td>28G</td>
+        </tr>
+    </tbody>
+</table>
+</div>
+Both Video-MME and OpenCompass were evaluated using 8×A100 GPUs for inference. The reported inference time of Video-MME excludes the cost of video frame extraction.
 ### Examples
 <div align="center">