Instructions to use moxin-org/MiniMax-M2.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moxin-org/MiniMax-M2.1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="moxin-org/MiniMax-M2.1-GGUF",
	filename="MXFP4_MOE/MiniMax-M2.1-MXFP4_MOE-00001-of-00007.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 moxin-org/MiniMax-M2.1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

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 moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

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 moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

LM Studio
Jan

vLLM

How to use moxin-org/MiniMax-M2.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moxin-org/MiniMax-M2.1-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": "moxin-org/MiniMax-M2.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

Ollama
How to use moxin-org/MiniMax-M2.1-GGUF with Ollama:
```
ollama run hf.co/moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
```

Unsloth Studio new

How to use moxin-org/MiniMax-M2.1-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 moxin-org/MiniMax-M2.1-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 moxin-org/MiniMax-M2.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for moxin-org/MiniMax-M2.1-GGUF to start chatting

Pi new

How to use moxin-org/MiniMax-M2.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

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": "moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use moxin-org/MiniMax-M2.1-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 moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

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 moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use moxin-org/MiniMax-M2.1-GGUF with Docker Model Runner:
```
docker model run hf.co/moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL
```

Lemonade

How to use moxin-org/MiniMax-M2.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moxin-org/MiniMax-M2.1-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.MiniMax-M2.1-GGUF-Q4_K_XL

List all available models

lemonade list

Moxin x llama.cpp Customized Quant for MiniMax-M2.1

We sincerely thank the open-source community developers and contributors unsloth for providing BF16 version and imatrix file.

We really appreciate the attention and we’re also happy to share additional quantization variants for everyone to try out and experiment with — hope you enjoy them!

- Q2_K_XL : 79.04 GiB (2.97 BPW)
- MXFP4_MOE : 115.27 GiB (4.33 BPW)
- Q4_K_XL : 129.72 GiB (4.87 BPW)
- Other Quant Versions (Coming soon)

👈 Download Guide

huggingface-cli download moxin-org/MiniMax-M2.1-GGUF --include "*Q2_K_XL*" --local-dir ./MiniMax-M2.1-GGUF

# !pip install huggingface_hub hf_transfer
import os
# os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id = "moxin-org/MiniMax-M2.1-GGUF",
    local_dir = "MiniMax-M2.1-GGUF",
    allow_patterns = ["*Q2_K_XL*"], # MXFP4_MOE
)

Download Available for huggingface_hub, huggingface-cli, snapshot_download, xet.

Usage

Example of runing gguf with local build of llama.cpp. (llama-cli/llama-server)

👈 Build llama.cpp locally

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp

# -DLLAMA_CURL=OFF if error
cmake -B build -DGGML_CUDA=ON -DBUILD_SHARED_LIBS=OFF 
cmake --build build --config Release -j --clean-first

build/bin/llama-cli -m MiniMax-M2.1-GGUF/Moxin-Q4_K_XL/MiniMax-M2.1-Q2_K_XL-00001-of-00004.gguf \
  -ngl 99 \
  --temp 1.0 \
  --top-k 40 \
  --top-p 0.95 \
  --min-p 0.01 \
  --ctx-size 8192 \ # 4096, 16384

Citation

If this work is helpful, please kindly helpe cite as:

@article{chen2025collaborative,
  title={Collaborative Compression for Large-Scale MoE Deployment on Edge},
  author={Chen, Yixiao and Xie, Yanyue and Yang, Ruining and Jiang, Wei and Wang, Wei and He, Yong and Chen, Yue and Zhao, Pu and Wang, Yanzhi},
  journal={arXiv preprint arXiv:2509.25689},
  year={2025}
}

Acknowledgements

This repository builds upon the outstanding work of the following open-source authors and projects:

We sincerely thank them for their excellent contributions to the open-source community.

Downloads last month: 12

GGUF

Model size

229B params

Architecture

minimax-m2

Hardware compatibility

2-bit

4-bit

Model tree for moxin-org/MiniMax-M2.1-GGUF

Base model

MiniMaxAI/MiniMax-M2.1

Quantized

(39)

this model

Collection including moxin-org/MiniMax-M2.1-GGUF

Moxin-GGUF

Collection

Moxin x llama.cpp Customized Quant for Large MoEs • 9 items • Updated Feb 27 • 3

Paper for moxin-org/MiniMax-M2.1-GGUF

Collaborative Compression for Large-Scale MoE Deployment on Edge

Paper • 2509.25689 • Published Sep 30, 2025