Instructions to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Abiray/MiniMax-M2.7-Q3_K_M-GGUF",
	filename="MiniMax-M2.7-Q3_K_M.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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

Use Docker

docker model run hf.co/Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abiray/MiniMax-M2.7-Q3_K_M-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": "Abiray/MiniMax-M2.7-Q3_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

Ollama
How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with Ollama:
```
ollama run hf.co/Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
```

Unsloth Studio

How to use Abiray/MiniMax-M2.7-Q3_K_M-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 Abiray/MiniMax-M2.7-Q3_K_M-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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Abiray/MiniMax-M2.7-Q3_K_M-GGUF to start chatting

How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_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": "Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Abiray/MiniMax-M2.7-Q3_K_M-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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_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 Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M
```

Lemonade

How to use Abiray/MiniMax-M2.7-Q3_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Abiray/MiniMax-M2.7-Q3_K_M-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.MiniMax-M2.7-Q3_K_M-GGUF-Q3_K_M

List all available models

lemonade list

Note: This is a Q3_K_M GGUF quantized version of the original MiniMaxAI/MiniMax-M2.7 model, packaged as a single massive file for seamless local deployment.

Join Our 💬 WeChat | 🧩 Discord community.

MiniMax Agent | ⚡️ API | MCP | MiniMax Website

🤗 Hugging Face | 🐙 GitHub | 🤖️ ModelScope | 📄 LICENSE

MiniMax-M2.7 is our first model deeply participating in its own evolution. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search. For more details, see our blog post.

Model Self-Evolution

M2.7 initiates a cycle of model self-evolution: during development, we let the model update its own memory, build dozens of complex skills for RL experiments, and improve its own learning process based on experiment results. An internal version of M2.7 autonomously optimized a programming scaffold over 100+ rounds — analyzing failure trajectories, modifying code, running evaluations, and deciding to keep or revert — achieving a 30% performance improvement. On MLE Bench Lite (22 ML competitions), M2.7 achieved a 66.6% medal rate, second only to Opus-4.6 and GPT-5.4.

Professional Software Engineering

M2.7 delivers outstanding real-world programming capabilities spanning log analysis, bug troubleshooting, refactoring, code security, and machine learning. Beyond code generation, M2.7 demonstrates strong system-level reasoning — correlating monitoring metrics, conducting trace analysis, verifying root causes in databases, and making SRE-level decisions. Using M2.7, we have reduced live production incident recovery time to under three minutes on multiple occasions.

Professional Work

M2.7 achieved an ELO score of 1495 on GDPval-AA (highest among open-source models), surpassing GPT5.3. It handles Word, Excel, and PPT with high-fidelity multi-round editing, producing editable deliverables. On Toolathon, M2.7 reached 46.3% accuracy (global top tier), and maintains 97% skill compliance across 40+ complex skills on MM Claw.

Entertainment

M2.7 features strengthened character consistency and emotional intelligence. We open-sourced OpenRoom, an interactive demo that places AI interaction within a Web GUI space with real-time visual feedback and scene interactions. Try it at openroom.ai.

GGUF Local Deployment Guide (llama.cpp)

This repository contains the MiniMax-M2.7-Q3_K_M.gguf model packaged as a single, large file.

Hardware Note: Due to the extreme parameter count of this model, even the quantized versions require significant system resources. Ensure you have adequate system RAM or VRAM to offload the model layers.

Run with llama.cpp

You can run this model natively using llama.cpp by pointing it to the .gguf file.

# Example CLI inference
./llama-cli -m /path/to/MiniMax-M2.7-Q3_K_M.gguf \
  -p "You are a helpful assistant. Your name is MiniMax-M2.7 and is built by MiniMax." \
  -n 512 -c 4096

Downloads last month: 95

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

3-bit

Model tree for Abiray/MiniMax-M2.7-Q3_K_M-GGUF

Base model

MiniMaxAI/MiniMax-M2.7

Quantized

(113)

this model

Collection including Abiray/MiniMax-M2.7-Q3_K_M-GGUF

MiniMax-M2.7

Collection

2 items • Updated Apr 13