Instructions to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio 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 Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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 Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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 Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

Use Docker

docker model run hf.co/Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

LM Studio
Jan

vLLM

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio",
		"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/Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

Ollama
How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with Ollama:
```
ollama run hf.co/Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
```
Unsloth Desktop

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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": "Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with Docker Model Runner:
```
docker model run hf.co/Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M
```

Lemonade

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

Run and chat with the model

lemonade run user.minicpm-v4_5-vqa-gguf-lmstudio-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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 Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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 "Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio: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"

MiniCPM-V 4.5 VQA Fine-tuned GGUF

This repository contains LM Studio / llama.cpp compatible GGUF files for a VQA fine-tuned MiniCPM-V 4.5 model.

Files

File	Description
`GGUF/ggml-model-Q4_K_M.gguf`	Quantized language model
`GGUF/mmproj-model-f16.gguf`	Vision / multimodal projector

llama.cpp

Recommended command:

llama-server -hf Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio:Q4_K_M --ctx-size 10000 --jinja --reasoning-budget 0

Manual command:

llama-server \
  -m GGUF/ggml-model-Q4_K_M.gguf \
  --mmproj GGUF/mmproj-model-f16.gguf \
  --ctx-size 10000 \
  --jinja \
  --reasoning-budget 0

Notes

This is a two-file multimodal GGUF setup.

ggml-model-Q4_K_M.gguf: language model
mmproj-model-f16.gguf: vision projector

LM Studio may display this as one downloadable model when it detects the companion mmproj file.

Downloads last month: 70

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for Hellohihihih/minicpm-v4_5-vqa-gguf-lmstudio

Base model

openbmb/MiniCPM-V-4_5

Quantized

huihui-ai/Huihui-MiniCPM-V-4_5-abliterated

Quantized

(3)

this model