Instructions to use dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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("dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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 dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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 "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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": "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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 "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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 dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX

Run Hermes

hermes

MLX LM

How to use dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-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 "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX

This repository contains an oMLX oQ4 mixed-precision MLX quantization of llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic.

This build follows the artifact lineage from llmfan46/MiniMax-M2.7-ultra-uncensored-heretic-GGUF. oMLX oQ quantization operates on MLX/safetensors checkpoints rather than GGUF files, so this build uses the corresponding BF16 safetensors checkpoint and excludes the existing GGUF quantizations.

Quantization

Field	Value
Method	oMLX oQ mixed-precision MLX
Quantization	oQ4
Model type	minimax_m2
Group size	64
Quantization mode	affine
Effective plan	4.57 bpw
Layer policy entries	250
Output shards	24 safetensors
Output size	121.7 GiB

Usage

huggingface-cli download dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX \
  --local-dir MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX

Then load it with an MLX-LM/oMLX runtime that supports minimax_m2:

python -m mlx_lm.generate \
  --model MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX \
  --prompt "Write a short greeting." \
  --max-tokens 64

Validation

Local validation completed with the bundled oMLX runtime on macOS:

model discovery: passed
model type: minimax_m2
quantization: bits=4, group_size=64, mode=affine
shards: 24

Source

BF16 source checkpoint: llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic
GGUF reference requested for this build: llmfan46/MiniMax-M2.7-ultra-uncensored-heretic-GGUF
Sensitivity proxy used during quantization: cookietimeh/MiniMax-M2.7-BF16-ultra-uncensored-heretic-mlx-4Bit
Quantization tool: oMLX oQ

Upstream model card license tag: other.

Downloads last month: 569

Safetensors

Model size

36B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX

Base model

MiniMaxAI/MiniMax-M2.7

Finetuned

amd/MiniMax-M2.7-BF16

Finetuned

llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic

Quantized

(6)

this model

Collection including dawncr0w/MiniMax-M2.7-ultra-uncensored-heretic-oQ4-MLX

MiniMax M2.7 MLX Models

Collection

Public MiniMax M2.7 MLX model repositories. • 1 item • Updated 11 days ago