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

Libraries

How to use openbmb/MiniCPM-V-4-gguf 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-gguf", 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-gguf", trust_remote_code=True, dtype="auto")

llama-cpp-python

How to use openbmb/MiniCPM-V-4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="openbmb/MiniCPM-V-4-gguf",
	filename="ggml-model-Q4_0.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use openbmb/MiniCPM-V-4-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openbmb/MiniCPM-V-4-gguf:Q4_K_M

Use Docker

docker model run hf.co/openbmb/MiniCPM-V-4-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use openbmb/MiniCPM-V-4-gguf 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-gguf"
# 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-gguf",
		"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-gguf:Q4_K_M

SGLang

How to use openbmb/MiniCPM-V-4-gguf 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-gguf" \
    --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-gguf",
		"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-gguf" \
        --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-gguf",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use openbmb/MiniCPM-V-4-gguf with Ollama:
```
ollama run hf.co/openbmb/MiniCPM-V-4-gguf:Q4_K_M
```

Unsloth Studio

How to use openbmb/MiniCPM-V-4-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openbmb/MiniCPM-V-4-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for openbmb/MiniCPM-V-4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for openbmb/MiniCPM-V-4-gguf to start chatting

Docker Model Runner
How to use openbmb/MiniCPM-V-4-gguf with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-4-gguf:Q4_K_M
```

Lemonade

How to use openbmb/MiniCPM-V-4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openbmb/MiniCPM-V-4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-4-gguf-Q4_K_M

List all available models

lemonade list

Error with ollama

by yokuto - opened Aug 6, 2025

Discussion

yokuto

Aug 6, 2025

I tried both Q8_0 and Q4_K_M, but encountered the following errors:
500: llama runner process has terminated: exit status 2
I'm experiencing same issues with RTX environments using Docker, as well as on Mac with native app.

tc-mb

OpenBMB org Aug 6, 2025

We have merged it into llama.cpp, but the PR I submitted to ollama has not been merged yet.
We will actively promote this matter.

yokuto

Aug 6, 2025

Thanks for answering.
There was no problem with using llama.cpp.

Ali4ai

Aug 10, 2025

Same error , below log if this help to solve issue

clip_model_loader: tensor[445]: n_dims = 1, name = v.blk.26.ln1.weight, tensor_size=4608, offset=938869376, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[446]: n_dims = 1, name = v.blk.26.ln1.bias, tensor_size=4608, offset=938873984, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[447]: n_dims = 2, name = v.blk.26.ffn_down.weight, tensor_size=9916416, offset=938878592, shape:[1152, 4304, 1, 1], type = f16
clip_model_loader: tensor[448]: n_dims = 1, name = v.blk.26.ffn_down.bias, tensor_size=17216, offset=948795008, shape:[4304, 1, 1, 1], type = f32
clip_model_loader: tensor[449]: n_dims = 2, name = v.blk.26.ffn_up.weight, tensor_size=9916416, offset=948812224, shape:[4304, 1152, 1, 1], type = f16
clip_model_loader: tensor[450]: n_dims = 1, name = v.blk.26.ffn_up.bias, tensor_size=4608, offset=958728640, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[451]: n_dims = 1, name = v.blk.26.ln2.weight, tensor_size=4608, offset=958733248, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[452]: n_dims = 1, name = v.blk.26.ln2.bias, tensor_size=4608, offset=958737856, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[453]: n_dims = 1, name = v.post_ln.weight, tensor_size=4608, offset=958742464, shape:[1152, 1, 1, 1], type = f32
clip_model_loader: tensor[454]: n_dims = 1, name = v.post_ln.bias, tensor_size=4608, offset=958747072, shape:[1152, 1, 1, 1], type = f32
load_hparams: projector: resampler
load_hparams: n_embd: 1152
load_hparams: n_head: 16
load_hparams: n_ff: 4304
load_hparams: n_layer: 27
load_hparams: projection_dim: 0
load_hparams: image_size: 448
load_hparams: patch_size: 14

load_hparams: has_llava_proj: 0
load_hparams: minicpmv_version: 5
load_hparams: proj_scale_factor: 0
load_hparams: n_wa_pattern: 0
load_hparams: ffn_op: gelu
load_hparams: model size: 914.34 MiB
load_hparams: metadata size: 0.16 MiB
load_tensors: loaded 455 tensors from E:\AI\Ollama\blobs\sha256-f0faa9ae63532300999c86a196f140c716cd0fbb08bbbd81850f1f9a631f7761
clip.cpp:3782: Unknown minicpmv version
time=2025-08-10T23:22:49.085+03:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-08-10T23:22:49.335+03:00 level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409"
[GIN] 2025/08/10 - 23:22:49 | 500 | 4.8977797s | 127.0.0.1 | POST "/api/generate"
time=2025-08-10T23:22:54.359+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0235821 runner.size="4.1 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=27496 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-10T23:22:54.608+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.2732448 runner.size="4.1 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=27496 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b
time=2025-08-10T23:22:54.859+03:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5234548 runner.size="4.1 GiB" runner.vram="3.2 GiB" runner.parallel=1 runner.pid=27496 runner.model=E:\AI\Ollama\blobs\sha256-b0ff610e9c92b30389ff1e0dd40fffed3c1f02a9d34a735fd5fba6a5ad25672b

Ali4ai

Aug 10, 2025

Thanks for answering.
There was no problem with using llama.cpp.

Hi , How to run it using llama.cpp if i download it from ollama , can use ollama blobs by llama.cpp

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment