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

Libraries

How to use krampenschiesser/MiniMax-M2.7-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="krampenschiesser/MiniMax-M2.7-GGUF",
	filename="minimax-m2.7-nvfp4.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use krampenschiesser/MiniMax-M2.7-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
# Run inference directly in the terminal:
llama-cli -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
# Run inference directly in the terminal:
llama-cli -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

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 krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

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 krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

Use Docker

docker model run hf.co/krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use krampenschiesser/MiniMax-M2.7-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krampenschiesser/MiniMax-M2.7-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": "krampenschiesser/MiniMax-M2.7-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

Ollama
How to use krampenschiesser/MiniMax-M2.7-GGUF with Ollama:
```
ollama run hf.co/krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
```

Unsloth Studio new

How to use krampenschiesser/MiniMax-M2.7-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 krampenschiesser/MiniMax-M2.7-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 krampenschiesser/MiniMax-M2.7-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use krampenschiesser/MiniMax-M2.7-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

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": "MiniMax-M2.7-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use krampenschiesser/MiniMax-M2.7-GGUF with Docker Model Runner:
```
docker model run hf.co/krampenschiesser/MiniMax-M2.7-GGUF:NVFP4
```

Lemonade

How to use krampenschiesser/MiniMax-M2.7-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull krampenschiesser/MiniMax-M2.7-GGUF:NVFP4

Run and chat with the model

lemonade run user.MiniMax-M2.7-GGUF-NVFP4

List all available models

lemonade list

These are some quants I use depending on the memory availability. I also added nvfp4 in the hope for custom kernels emerging in the future. I recommend the Q3K-IQ4XS and IQ4XS-Q5K quants.

KLD

I need to use the Q8 version due to hardware restrictions for running the kld baseline. However it is quantized in the same way as the original model which also uses 8 bits for the expert weights so the difference should not be big.

Sadly I am getting weird outputs (nan floats from llama-perplexity) from some kld runs so take this with a salt lake.

Provider	Quant	Size GB	Mean PPL	Mean KLD	Same Top p
KS	Q8		7.0266 +/- 0.05210	baseline	baseline
KS	IQ4XS-Q5K	135.5			90.720 ± 0.077 %
KS	IQ4XS	123.8	7.153799 ± 0.053213	0.086127 ± 0.001029	89.425 ± 0.082 %
KS	IQ4XS-Q4K	126.1			89.205 ± 0.083 %
KS	NVFP4	130.8	7.177182 ± 0.053324	0.105053 ± 0.001034	88.154 ± 0.086 %
unsloth	UD-Q4_K_XL	141			86.990 ± 0.090 %
KS	Q3K-IQ4XS	108.6	7.297092 ± 0.054489	0.140361 ± 0.001216	86.387 ± 0.091 %

Downloads last month: 3,556

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

4-bit

View +2 variants

Model tree for krampenschiesser/MiniMax-M2.7-GGUF

Base model

MiniMaxAI/MiniMax-M2.7

Quantized

(103)

this model