Instructions to use ahoybrotherbear/MiniMax-M2.5-4bit-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ahoybrotherbear/MiniMax-M2.5-4bit-MLX 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("ahoybrotherbear/MiniMax-M2.5-4bit-MLX")

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 ahoybrotherbear/MiniMax-M2.5-4bit-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"

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": "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ahoybrotherbear/MiniMax-M2.5-4bit-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"

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 "ahoybrotherbear/MiniMax-M2.5-4bit-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

MLX LM

How to use ahoybrotherbear/MiniMax-M2.5-4bit-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "ahoybrotherbear/MiniMax-M2.5-4bit-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use ahoybrotherbear/MiniMax-M2.5-4bit-MLX 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 "ahoybrotherbear/MiniMax-M2.5-4bit-MLX"

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 ahoybrotherbear/MiniMax-M2.5-4bit-MLX

Run Hermes

hermes

MiniMax-M2.5 4-bit MLX

This is a 4-bit quantized MLX version of MiniMaxAI/MiniMax-M2.5, converted using mlx-lm v0.29.1.

MiniMax-M2.5 is a 229B parameter Mixture of Experts model (10B active parameters) that achieves 80.2% on SWE-Bench Verified and is SOTA in coding, agentic tool use, and search tasks.

Requirements

Apple Silicon Mac (M3 Ultra or later recommended)
At least 256GB of unified memory

Quick Start

Install mlx-lm:

pip install -U mlx-lm

CLI

mlx_lm.generate \
  --model ahoybrotherbear/MiniMax-M2.5-4bit-MLX \
  --prompt "Hello, how are you?" \
  --max-tokens 256 \
  --temp 0.7

Python

from mlx_lm import load, generate

model, tokenizer = load("ahoybrotherbear/MiniMax-M2.5-4bit-MLX")

messages = [{"role": "user", "content": "Hello, how are you?"}]
prompt = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

response = generate(
    model, tokenizer,
    prompt=prompt,
    max_tokens=256,
    temp=0.7,
    verbose=True
)
print(response)

Conversion Details

Source model: MiniMaxAI/MiniMax-M2.5 (FP8)
Converted with: mlx-lm v0.29.1
Quantization: 4-bit
Original parameters: 229B total / 10B active (MoE)

Original Model

MiniMax-M2.5 was created by MiniMaxAI. See the original model card for full details on capabilities, benchmarks, and license terms.

Downloads last month: 15

Safetensors

Model size

229B params

Tensor type

BF16

U32

F32

MLX

Hardware compatibility

4-bit

Model tree for ahoybrotherbear/MiniMax-M2.5-4bit-MLX

Base model

MiniMaxAI/MiniMax-M2.5

Quantized

(63)

this model