Instructions to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4",
	filename="MiniMax-M2.5-REAP-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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
# Run inference directly in the terminal:
llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

Use Docker

docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

LM Studio
Jan

vLLM

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

Ollama
How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with Ollama:
```
ollama run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
```

Unsloth Studio new

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 to start chatting

Pi new

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

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": "BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

Run Hermes

hermes

Docker Model Runner
How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with Docker Model Runner:
```
docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE
```

Lemonade

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4:MXFP4_MOE

Run and chat with the model

lemonade run user.MiniMax-M2.5-REAP-139B-A10B-MXFP4-MXFP4_MOE

List all available models

lemonade list

MiniMax-M2.5-REAP-139B-A10B-MXFP4

When you want MoE-specific compression without sending quality into the abyss.

Built from:

Base: MiniMaxAI/MiniMax-M2.5
REAP source: tomngdev/MiniMax-M2.5-REAP-139B-A10B-GGUF (BF16 split)
Quantized locally with llama.cpp as MXFP4_MOE.

Quant

Quant	Size (GiB)	Notes
`MXFP4_MOE`	70.91	MoE-oriented quantization, with many non-expert tensors preserved at higher precision

Tensor Mix

This quant uses a mixed layout (as expected for MXFP4 MoE), including mxfp4, q8_0, and f32 tensors.

Usage

Use the first shard; llama.cpp resolves the rest:

llama-cli -m MiniMax-M2.5-REAP-MXFP4_MOE-00001-of-00007.gguf -ngl 0 -c 8192

Why a Separate Repo

MXFP4 has a different target audience than standard Q-series packs, so it gets its own clean home and simpler download surface.

Credits

MiniMaxAI for MiniMax-M2.5
tomngdev for the BF16 REAP GGUF release
BennyDaBall for this quant

Disclaimer

You are responsible for your own use, outputs, and compliance with applicable laws and platform policies.

Downloads last month: 25

GGUF

Model size

139B params

Architecture

minimax-m2

Hardware compatibility

4-bit

Model tree for BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-MXFP4

Base model

MiniMaxAI/MiniMax-M2.5

Quantized

cerebras/MiniMax-M2.5-REAP-139B-A10B

Quantized

tomngdev/MiniMax-M2.5-REAP-139B-A10B-GGUF

Quantized

(2)

this model