Instructions to use inferencerlabs/MiniMax-M2.7-MLX-9bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/MiniMax-M2.7-MLX-9bit 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("inferencerlabs/MiniMax-M2.7-MLX-9bit")

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
LM Studio

Pi new

How to use inferencerlabs/MiniMax-M2.7-MLX-9bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/MiniMax-M2.7-MLX-9bit"

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": "inferencerlabs/MiniMax-M2.7-MLX-9bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use inferencerlabs/MiniMax-M2.7-MLX-9bit 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 "inferencerlabs/MiniMax-M2.7-MLX-9bit"

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 inferencerlabs/MiniMax-M2.7-MLX-9bit

Run Hermes

hermes

MLX LM

How to use inferencerlabs/MiniMax-M2.7-MLX-9bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "inferencerlabs/MiniMax-M2.7-MLX-9bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "inferencerlabs/MiniMax-M2.7-MLX-9bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "inferencerlabs/MiniMax-M2.7-MLX-9bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Issue with config.json

by onesNzeros - opened Apr 13

Discussion

onesNzeros

Apr 13

Thanks for sharing this . I think your config.json is missing some quantization details or possibly the wrong config.json for this quantized model.

inferencerlabs

Owner Apr 13

What are you using to inference the model?

onesNzeros

Apr 14

On a M3 Ultra 512GB using mlx-lm 0.31.1. It throws a KeyError for 'quant_method ' when 'mlx_lm/utils.py' tries to load quant_method = quantization_config["quant_method"]. I was able to get it going by modifying the 'quantization_config' key in config.json like so.

"quantization": {
        "group_size": 32,
        "bits": 8,
        "mode": "affine",
        "model.layers.0.block_sparse_moe.gate": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.block_sparse_moe.gate": {
            "group_size": 64,
            "bits": 8
        },

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