Instructions to use mlx-community/MiniMax-M2-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/MiniMax-M2-4bit with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M2-4bit")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/MiniMax-M2-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/MiniMax-M2-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/MiniMax-M2-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/MiniMax-M2-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/MiniMax-M2-4bit"

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 mlx-community/MiniMax-M2-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/MiniMax-M2-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/MiniMax-M2-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/MiniMax-M2-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/MiniMax-M2-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MiniMax-M2-4bit not supported

by garryo - opened Oct 30, 2025

Discussion

garryo

MLX Community org Oct 30, 2025

when running the example command on my MAC Studio M3 Ultra with 512GB of memory I get:

(MiniMax-M2) gbobafett@bobafetts-Mac-Studio MiniMax-M2 % uv pip show mlx-lm
Name: mlx-lm
Version: 0.28.3
Location: /Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/.venv/lib/python3.12/site-packages
Requires: jinja2, mlx, numpy, protobuf, pyyaml, transformers
Required-by:
(MiniMax-M2) bobafett@bobafetts-Mac-Studio MiniMax-M2 % python example.py
Fetching 37 files: 100%|███████████████████████████████████████████████| 37/37 [00:00<00:00, 6432.45it/s]
ERROR:root:Model type minimax not supported.
Traceback (most recent call last):
File "/Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/.venv/lib/python3.12/site-packages/mlx_lm/utils.py", line 68, in _get_classes
arch = importlib.import_module(f"mlx_lm.models.{model_type}")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/garryosborne/.local/share/uv/python/cpython-3.12.9-macos-aarch64-none/lib/python3.12/importlib/__init__.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 1387, in _gcd_import
File "", line 1360, in _find_and_load
File "", line 1324, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'mlx_lm.models.minimax'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/example.py", line 4, in
model, tokenizer = load("mlx-community/MiniMax-M2-4bit")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/.venv/lib/python3.12/site-packages/mlx_lm/utils.py", line 266, in load
model, config = load_model(model_path, lazy, model_config=model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/.venv/lib/python3.12/site-packages/mlx_lm/utils.py", line 178, in load_model
model_class, model_args_class = get_model_classes(config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Volumes/AI_MODELS_2/MoreModels/MiniMax-M2/.venv/lib/python3.12/site-packages/mlx_lm/utils.py", line 72, in _get_classes
raise ValueError(msg)
ValueError: Model type minimax not supported.

Noodlz

Oct 31, 2025

I got the same issue. im assuming its because the model support is coming in the 0.28.4 version, whereas the version released and what we have available is 0.28.3

kernelpool

MLX Community org Oct 31, 2025

Correct, support is merged but 0.28.4 is yet to be released.

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