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

Libraries

How to use unsloth/MiniMax-M2.5-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/MiniMax-M2.5-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/MiniMax-M2.5-GGUF", dtype="auto")

llama-cpp-python

How to use unsloth/MiniMax-M2.5-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/MiniMax-M2.5-GGUF",
	filename="BF16/MiniMax-M2.5-BF16-00001-of-00010.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 unsloth/MiniMax-M2.5-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/MiniMax-M2.5-GGUF:UD-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 unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/MiniMax-M2.5-GGUF:UD-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 unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/MiniMax-M2.5-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/MiniMax-M2.5-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": "unsloth/MiniMax-M2.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/MiniMax-M2.5-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/MiniMax-M2.5-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/MiniMax-M2.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/MiniMax-M2.5-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/MiniMax-M2.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/MiniMax-M2.5-GGUF with Ollama:
```
ollama run hf.co/unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
```

Unsloth Studio new

How to use unsloth/MiniMax-M2.5-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 unsloth/MiniMax-M2.5-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 unsloth/MiniMax-M2.5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/MiniMax-M2.5-GGUF to start chatting

Pi new

How to use unsloth/MiniMax-M2.5-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/MiniMax-M2.5-GGUF:UD-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": "unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/MiniMax-M2.5-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 unsloth/MiniMax-M2.5-GGUF:UD-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 unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Docker Model Runner
How to use unsloth/MiniMax-M2.5-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/MiniMax-M2.5-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/MiniMax-M2.5-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.MiniMax-M2.5-GGUF-UD-Q4_K_XL

List all available models

lemonade list

4-bit quantization: MXFP4_MOE vs Q4_K_XL?

by fsaudm - opened Feb 14

Discussion

fsaudm

Feb 14

Just wanting to get some insights from the community. Running this model with llama.cpp (I think the best for running gguf, though feedback/comments on this are also welcome :D ) on a 140GB H200. Why one over the other? speed? "intelligence"?

Thanks!!

danielhanchen

Unsloth AI org Feb 15

MXFP4 is apparently much faster at the cost of slight quality.

dugrema

Feb 15

I tried mxfp4 on llama.cpp, since I don't have enough VRAM to fit the whole model on GPU I'm not surprised I didn't notice any speed difference. When using tools I can't say I saw a difference in behavior, but I didn't test it much. I'll stick with Q4_K_XL.

So only reason I would switch to it is if it gave me more token/s - and in my case it does not.

Also my overall impression on GLM 4.7 Flash (Q4) after a few weeks is that I prefer it over gpt-oss 20B (my other main model) for design, planning and troubleshooting. But at some point it starts spinning its wheel during implementation, so I switch back to gpt-oss and that usually takes the job passed the finish line. It's been a good combo for me over the last 2 weeks.

Shuasimodo

Feb 16

•

edited Feb 16

MXFP4 is apparently much faster at the cost of slight quality.

Everybody's mxfp4 quants use f32/q8/mxfp4 for precision except gpt oss models, it uses f32/f16/mxfp4.
Which makes it much faster (f32/q8_0/mxfp4) but degrades the quality quite a lot where the gpt oss models have higher quality output.

Easiest way to notice without getting too into the weeds is comparing the gpt oss 20b models. And also looking at their structure versus all other mxfp4 gguf quants.

I think this has a lot to do why the gpt oss models are so good in mxfp4 format, while all the rest are just known to be faster at the expense of quality.

https://huggingface.co/ggml-org/gpt-oss-20b-GGUF/blob/main/gpt-oss-20b-mxfp4.gguf - q8_0/f32/mxfp4, 12.1gb.
https://huggingface.co/unsloth/gpt-oss-20b-GGUF/blob/main/gpt-oss-20b-F16.gguf - f16/f32/mxfp4 , 13.8gb

The ollama model is the same as the unsloth and notably way better than the ggml version in terms of accuracy and coherency:
https://ollama.com/library/gpt-oss:20b/blobs/e7b273f96360, bf16/f32/mxfp4, 14gb.

this is the same across the board. All current mxfp4 gguf quants are structured like the ggml as far can I can tell. unsloth, noctrex, ggml, etc... all gguf mxfp4's.
Qwen3-coder-next for example, same structure: https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF/blob/main/Qwen3-Coder-Next-MXFP4_MOE.gguf

When pitting the models directly against eachother (eg. gpt oss 20b/120b from ggml or other quantizers versus the ollama version or the unsloth version) the ollama and unsloth are notably slower, and prompt processing is a little slower, but they are also very notably more accurate. The size difference doesn't seem to significant. ~2gb difference between the two 120b models.

Also for argument sake, "the difference bettween f16 and q8_0 is negligible" is fine for roleplaying. But for coding, research, or agentic tasks is a lot more noticeable than negligible.

olka-fi

Feb 17

•

edited Feb 17

Thanks for your work Daniel!

MXFP4 is apparently much faster at the cost of slight quality.

Is it possible to see somewhere comparison how big exactly this quality drop?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment