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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF 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-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": "BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Ollama
How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF with Ollama:
```
ollama run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF with Docker Model Runner:
```
docker model run hf.co/BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniMax-M2.5-REAP-139B-A10B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_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 BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "BennyDaBall/MiniMax-M2.5-REAP-139B-A10B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiniMax-M2.5-REAP-139B-A10B-GGUF / README.md

BennyDaBall

Add model card

d755148 verified 7 months ago

1.52 kB

license: other
base_model:
  - MiniMaxAI/MiniMax-M2.5
language:
  - en
tags:
  - gguf
  - minimax
  - moe
  - reap
  - text-generation
pipeline_tag: text-generation

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

This is the REAP model in practical pants: high quality GGUF quants for local inference without setting your workstation on fire.

Built from:

Base: MiniMaxAI/MiniMax-M2.5
REAP source: tomngdev/MiniMax-M2.5-REAP-139B-A10B-GGUF (BF16 split)
Quantized locally with llama.cpp on Strix Halo + high RAM mode.

Available Quants

Quant	Status	Size (GiB)	Notes
`Q8_0`	uploaded	137.78	Highest quality quant in this pack
`Q5_K_M`	processing/uploading	TBD	Better quality/size balance
`Q4_K_M`	uploaded	78.83	Strong practical default

File Layout

All quants are split GGUF sets (00001-of-00007 etc.) for safer handling of very large models.

Quality Notes

These are generated from BF16 REAP GGUF, not requantized from lower precision.
Token embedding and output tensors are kept at Q8_0 during quantization for quality retention.

Usage

Use any first shard with llama.cpp; it auto-discovers sibling shards:

llama-cli -m MiniMax-M2.5-REAP-Q4_K_M-00001-of-00007.gguf -ngl 0 -c 8192

Credits

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

Disclaimer

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