Instructions to use dealignai/MiniMax-M2.5-JANG_3L-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dealignai/MiniMax-M2.5-JANG_3L-CRACK 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("dealignai/MiniMax-M2.5-JANG_3L-CRACK")

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 dealignai/MiniMax-M2.5-JANG_3L-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/MiniMax-M2.5-JANG_3L-CRACK"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "dealignai/MiniMax-M2.5-JANG_3L-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use dealignai/MiniMax-M2.5-JANG_3L-CRACK with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "dealignai/MiniMax-M2.5-JANG_3L-CRACK"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "dealignai/MiniMax-M2.5-JANG_3L-CRACK"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "dealignai/MiniMax-M2.5-JANG_3L-CRACK",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use dealignai/MiniMax-M2.5-JANG_3L-CRACK 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 "dealignai/MiniMax-M2.5-JANG_3L-CRACK"

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 dealignai/MiniMax-M2.5-JANG_3L-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use dealignai/MiniMax-M2.5-JANG_3L-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "dealignai/MiniMax-M2.5-JANG_3L-CRACK"

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 "dealignai/MiniMax-M2.5-JANG_3L-CRACK" \
  --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"

Important: This model uses the JANG quantization format — the GGUF equivalent for MLX on Apple Silicon. Currently only supported by MLX Studio and the jang-tools Python package.

MLX Studio — the only app that natively supports JANG models

⚡ All JANG models are meant to be run in vMLX

MiniMax M2.5 — JANG_3L + CRACK

JANG mixed-precision · CRACK abliterated · No guardrails · 89 GB

What Is This?

This is MiniMax M2.5 — a 230B parameter Mixture-of-Experts model with 256 experts (8 active per token), all standard attention (no SSM), and trained with chain-of-thought reasoning.

It has been:

JANG quantized — JANG_3L profile (8-bit attention, 4-bit important, 3-bit experts) — 89 GB
CRACK abliterated — permanent weight-level removal of safety refusal


Architecture	MiniMax M2.5 MoE — 230B total, ~10B active, 256 experts
Quantization	JANG_3L (8/4/3-bit mixed, 3.08 avg) — 89 GB
Abliteration	CRACK abliterated
MMLU-208	91.8% (4 subjects at 100%)
Compliance	8/8 prompts
Speed	~46 tok/s (M4 Ultra 256 GB)
Fits on	128 GB+ Macs

MMLU-208 Results (Per Subject)

Subject	Score
College Physics	16/16 (100%)
Conceptual Physics	16/16 (100%)
Professional Medicine	16/16 (100%)
High School Biology	16/16 (100%)
Abstract Algebra	15/16 (94%)
College Mathematics	15/16 (94%)
High School Geography	15/16 (94%)
World Religions	15/16 (94%)
College Computer Science	14/16 (88%)
Machine Learning	14/16 (88%)
Electrical Engineering	13/16 (81%)
Formal Logic	13/16 (81%)
High School Mathematics	13/16 (81%)
Total	191/208 (91.8%)

CRACK surgery with proper probe vectors actually improves reasoning on MiniMax. Safety guardrails were constraining the model's full reasoning capacity.

vs JANG_2L CRACK

	JANG_2L	JANG_3L
Avg bits	2.1	3.08
Size	63 GB	89 GB
MMLU	84.7%	91.8%
Compliance	7/8	8/8
Fits on	96 GB Mac	128 GB Mac

Higher precision quantization = better reasoning AND compliance.

Install & Usage

pip install "jang[mlx]"

from jang_tools import load_for_inference
from mlx_lm import generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load_for_inference("dealignai/MiniMax-M2.5-JANG_3L-CRACK")
sampler = make_sampler(temp=1.0)  # MiniMax requires temp=1.0 for chat

messages = [{"role": "user", "content": "Your prompt here"}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False)

response = generate(model, tokenizer, prompt=prompt, max_tokens=2000, sampler=sampler)
print(response)

Disable Thinking (direct answers)

prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False,
    enable_thinking=False)

Note: MiniMax generates a <think> chain before answering by default. Use max_tokens=2000+ for complex questions. For chat, use temperature=1.0 (greedy causes loops).

About JANG

JANG (Jang Adaptive N-bit Grading) is a mixed-precision quantization format for Apple Silicon — the GGUF equivalent for MLX. Classifies tensors into sensitivity tiers and assigns bits accordingly.

About CRACK

CRACK (Controlled Refusal Ablation via Calibrated Knockouts) removes safety alignment from LLMs at the weight level. This model has been abliterated using proprietary techniques achieving full compliance while preserving reasoning quality.

Disclaimer

This model is provided for research and educational purposes. The creators are not responsible for any misuse. By downloading this model, you agree to use it responsibly and in compliance with applicable laws.

한국어