Instructions to use openbmb/MiniCPM-V-4.6-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openbmb/MiniCPM-V-4.6-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-4.6-gguf")
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-4.6-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use openbmb/MiniCPM-V-4.6-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf openbmb/MiniCPM-V-4.6-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-4.6-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf openbmb/MiniCPM-V-4.6-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-4.6-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Use Docker

docker model run hf.co/openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use openbmb/MiniCPM-V-4.6-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-4.6-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-4.6-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-4.6-gguf:Q4_K_M

SGLang

How to use openbmb/MiniCPM-V-4.6-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-4.6-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-4.6-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-4.6-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-4.6-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-4.6-gguf with Ollama:
```
ollama run hf.co/openbmb/MiniCPM-V-4.6-gguf:Q4_K_M
```
Unsloth Desktop

How to use openbmb/MiniCPM-V-4.6-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "openbmb/MiniCPM-V-4.6-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use openbmb/MiniCPM-V-4.6-gguf with Docker Model Runner:
```
docker model run hf.co/openbmb/MiniCPM-V-4.6-gguf:Q4_K_M
```

Lemonade

How to use openbmb/MiniCPM-V-4.6-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-4.6-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use openbmb/MiniCPM-V-4.6-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use openbmb/MiniCPM-V-4.6-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf openbmb/MiniCPM-V-4.6-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "openbmb/MiniCPM-V-4.6-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

not working with llama.cpp

by phmzo - opened 24 days ago

Discussion

phmzo

24 days ago

•

edited 24 days ago

When I run this model and upload an image, the llama.cpp throws:
In the UI: Error: "This model supports: text files, PDFs"
through the local API: "image input is not supported - hint: if this is unexpected, you may need to provide the mmproj"

{
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "describe this image"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,/9j/4AAQ...
          }
        }
      ]
    }
  ],
  "model": "MiniCPM-V-4_6-F16",
  "mmproj":"mmproj-model-f16"
}

logs:

[51243] 0.01.938.469 I srv          init: init: chat template, thinking = 1
[51243] 0.01.938.493 I srv          main: model loaded
[51243] 0.01.938.495 I srv          main: server is listening on http://127.0.0.1:51243
[51243] cmd_child_to_router:ready
[51243] cmd_child_to_router:info:{"id":"MiniCPM-V-4_6-Q4_K_M","aliases":["MiniCPM-V-4_6-Q4_K_M"],"tags":[],"object":"model","created":1786180099,"owned_by":"llamacpp","meta":{"vocab_type":2,"n_vocab":248094,"n_ctx":262144,"n_ctx_train":262144,"n_embd":1024,"n_params":752161600,"size":518145904}}
0.32.966.450 I srv  proxy_reques: proxying request to model MiniCPM-V-4_6-Q4_K_M on port 51243
[51243] 0.01.938.689 I srv  update_slots: all slots are idle
[51243] 0.01.938.694 I srv    operator(): child server monitoring thread started, waiting for EOF on stdin...
[51243] 0.01.939.675 W srv    operator(): got exception: {"error":{"code":500,"message":"image input is not supported - hint: if this is unexpected, you may need to provide the mmproj","type":"server_error"}}

Tested with Q4, then F16, with mmproj:

tc-mb

OpenBMB org 24 days ago

@fawogin598
This is a usage/configuration issue rather than a model support issue.
The "mmproj" field in the OpenAI request body is not supported and will not load the projector.
The projector must be specified when starting llama.cpp:

llama-server \
  -m MiniCPM-V-4_6-Q4_K_M.gguf \
  --mmproj mmproj-model-f16.gguf

You can refer to this document for guidance. It might be helpful.
https://github.com/OpenSQZ/MiniCPM-V-CookBook/blob/main/deployment/llama.cpp/minicpm-v4_6_llamacpp.md

phmzo

13 days ago

Thanks @tc-mb for the reply,
My issue was in a multi-model setup for llama-server (no --mmproj, I'm not that dumb).
Never mind, I fixed it.
GGUF is supposed to include mmproj to solve all these issues from the past (need of mmproj, location of it, name of it).

tc-mb

OpenBMB org 13 days ago

@fawogin598
I'm glad to hear that you have solved this problem, so I'll close this issue.
If you have any questions, you are welcome to discuss the issue at any time.

tc-mb changed discussion status to closed 13 days ago

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