Instructions to use tonjum/MiniMax-M3-EAGLE3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tonjum/MiniMax-M3-EAGLE3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tonjum/MiniMax-M3-EAGLE3-GGUF",
	filename="MiniMax-M3-EAGLE3-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use tonjum/MiniMax-M3-EAGLE3-GGUF with Ollama:
```
ollama run hf.co/tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
```

Unsloth Studio

How to use tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-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 tonjum/MiniMax-M3-EAGLE3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tonjum/MiniMax-M3-EAGLE3-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tonjum/MiniMax-M3-EAGLE3-GGUF with Docker Model Runner:
```
docker model run hf.co/tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M
```

Lemonade

How to use tonjum/MiniMax-M3-EAGLE3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tonjum/MiniMax-M3-EAGLE3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniMax-M3-EAGLE3-GGUF-Q4_K_M

List all available models

lemonade list

MiniMax-M3-EAGLE3 Draft Models

These are quantized EAGLE3 draft models for speculative decoding with MiniMax-M3.

Note: This requires a special build of llama.cpp with MiniMax M3 + EAGLE3 support. See build instructions below.

Building llama.cpp with MiniMax M3 + EAGLE3 support

Option 1: Using the PR (recommended)

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
git fetch origin pull/24925/head:minimax-m3-eagle3
git checkout minimax-m3-eagle3
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j --target llama-cli llama-server

Option 2: Using the fork

git clone https://github.com/nick-tonjum/llama.cpp-minimax-m3-eagle3
cd llama.cpp-minimax-m3-eagle3
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release -j --target llama-cli llama-server

Usage

llama-server \
  -m /path/to/minimax-m3-base-model.gguf \
  -md /path/to/MiniMax-M3-EAGLE3-Q4_K_M.gguf \
  --spec-type draft-eagle3 \
  --fit on --fit-target 1024 --fit-ctx 131072

Downloads last month: 4,052

GGUF

Model size

3B params

Architecture

eagle3

Hardware compatibility

2-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tonjum/MiniMax-M3-EAGLE3-GGUF

Base model

MiniMaxAI/Minimax-M3-preview

Finetuned

Inferact/MiniMax-M3-EAGLE3

Quantized

(2)

this model