Instructions to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD",
	filename="IQ4_XS/MiniMax-M2.7-abliterated-IQ4_XS-00001-of-00010.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
# Run inference directly in the terminal:
llama-cli -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

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 GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

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 GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

Use Docker

docker model run hf.co/GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

LM Studio
Jan

vLLM

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

Ollama
How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with Ollama:
```
ollama run hf.co/GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
```

Unsloth Studio

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD 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 GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD 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 GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD to start chatting

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

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": "GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

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 GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with Docker Model Runner:
```
docker model run hf.co/GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS
```

Lemonade

How to use GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD:IQ4_XS

Run and chat with the model

lemonade run user.MiniMax-M2.7-Abliterated-Heretic-GGUF-UD-IQ4_XS

List all available models

lemonade list

I'm using the Youssofal/MiniMax-M2.7-Abliterated-Heretic-GGUF model, but the q4 quantizations provided in the repository don't fit my system configuration (128GB RAM + 16GB VRAM), so I took the imatrix from unsloth (https://huggingface.co/unsloth/MiniMax-M2.7-GGUF/tree/main) and used their weights for quantization. Thanks a lot!

The advantage of unsloth's quantization is that it encodes different tensors with different precisions depending on their importance, so more important tensors are encoded with less loss. In the original (Youssofal) GGUF repository, all tensors are encoded with the same precision, which results in a significant loss of quality compared to unsloth's gguf.

So I tried to combine the best of both worlds.

Downloads last month: 612

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

4-bit

Model tree for GreyManul/MiniMax-M2.7-Abliterated-Heretic-GGUF-UD

Base model

MiniMaxAI/MiniMax-M2.7

Quantized

Youssofal/MiniMax-M2.7-Abliterated-Heretic-GGUF

Quantized

(2)

this model