Instructions to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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("prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF", dtype="auto")

llama-cpp-python

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF",
	filename="MiniCPM-V-4.6-abliterated-MAX.BF16.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

llama.cpp

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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": "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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/prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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": "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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": "prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
```

Unsloth Studio new

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF to start chatting

Pi new

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-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 prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-4.6-abliterated-MAX-GGUF-Q4_K_M

List all available models

lemonade list

MiniCPM-V-4.6-abliterated-MAX-GGUF

MiniCPM-V-4.6-abliterated-MAX is an abliterated evolution built on top of openbmb/MiniCPM-V-4.6. This model applies advanced refusal direction analysis and ablation-based optimization strategies to reduce internal refusal behaviors while preserving the multimodal reasoning and instruction-following strengths of the original architecture. The result is a highly capable and ultra-efficient multimodal language model optimized for image, video, and text understanding with improved instruction adherence.

This model is intended for research and learning purposes only. It reduces internal refusal behaviors, and any content generated by it is used at the user’s own risk. The authors and hosting page disclaim any liability for outputs produced by this model. Users are responsible for ensuring safe, ethical, and lawful usage.

Getting Started with llama.cpp Using Docker

FROM ghcr.io/ggml-org/llama.cpp:full

WORKDIR /app

# Install minimal dependencies required for creating a Python virtual environment
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3-pip python3-venv \
    && rm -rf /var/lib/apt/lists/*

# Create virtual environment
RUN python3 -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Install Python packages inside the virtual environment only
RUN pip install --no-cache-dir -U huggingface_hub

# Download model and mmproj
RUN python3 -c 'from huggingface_hub import hf_hub_download; \
    repo="prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF"; \
    hf_hub_download(repo_id=repo, filename="MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf", local_dir="/app"); \
    hf_hub_download(repo_id=repo, filename="MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf", local_dir="/app")'

CMD ["--server", \
     "-m", "/app/MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf", \
     "--mmproj", "/app/MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf", \
     "--host", "0.0.0.0", \
     "--port", "7860", \
     "-t", "3", \
     "--mlock", \
     "--prio", "3", \
     "--swa-full", \
     "--no-slots", \
     "-ngl", "99", \
     "--mmap", \
     "--log-disable", \
     "--skip-chat-parsing", \
     "--no-cont-batching", \
     "--threads-http", "1", \
     "--direct-io", \
     "--no-repack", \
     "--flash-attn", "off", \
     "-c", "640000", \
     "-n", "389012"]

Model Files

File Name	Quant Type	File Size	File Link
MiniCPM-V-4.6-abliterated-MAX.BF16.gguf	BF16	1.52 GB	Download
MiniCPM-V-4.6-abliterated-MAX.F16.gguf	F16	1.52 GB	Download
MiniCPM-V-4.6-abliterated-MAX.F32.gguf	F32	3.02 GB	Download
MiniCPM-V-4.6-abliterated-MAX.Q2_K.gguf	Q2_K	422 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q3_K_L.gguf	Q3_K_L	491 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q3_K_M.gguf	Q3_K_M	466 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q3_K_S.gguf	Q3_K_S	435 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q4_0.gguf	Q4_0	501 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q4_K_M.gguf	Q4_K_M	529 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q4_K_S.gguf	Q4_K_S	505 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q5_0.gguf	Q5_0	563 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q5_K_M.gguf	Q5_K_M	578 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q5_K_S.gguf	Q5_K_S	563 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q6_K.gguf	Q6_K	630 MB	Download
MiniCPM-V-4.6-abliterated-MAX.Q8_0.gguf	Q8_0	812 MB	Download
MiniCPM-V-4.6-abliterated-MAX.mmproj-bf16.gguf	mmproj-bf16	1.11 GB	Download
MiniCPM-V-4.6-abliterated-MAX.mmproj-f16.gguf	mmproj-f16	1.11 GB	Download
MiniCPM-V-4.6-abliterated-MAX.mmproj-f32.gguf	mmproj-f32	2.19 GB	Download
MiniCPM-V-4.6-abliterated-MAX.mmproj-q8_0.gguf	mmproj-q8_0	728 MB	Download

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 2,771

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF

Base model

openbmb/MiniCPM-V-4.6

Finetuned

prithivMLmods/MiniCPM-V-4.6-abliterated-MAX

Quantized

(3)

this model

Dataset used to train prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF

Collection including prithivMLmods/MiniCPM-V-4.6-abliterated-MAX-GGUF

MiniCPM-V-4.6/5.0 — abliterated/uncensored

Collection

Collection of Uncensored Variants of MiniCPM-V-4.6 Multimodal Models • 4 items • Updated about 11 hours ago • 2