Instructions to use JANGQ-AI/MiniMax-M2.7-JANG_4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JANGQ-AI/MiniMax-M2.7-JANG_4M 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("JANGQ-AI/MiniMax-M2.7-JANG_4M")

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 JANGQ-AI/MiniMax-M2.7-JANG_4M with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "JANGQ-AI/MiniMax-M2.7-JANG_4M"

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": "JANGQ-AI/MiniMax-M2.7-JANG_4M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use JANGQ-AI/MiniMax-M2.7-JANG_4M 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 "JANGQ-AI/MiniMax-M2.7-JANG_4M"

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 JANGQ-AI/MiniMax-M2.7-JANG_4M

Run Hermes

hermes

MLX LM

How to use JANGQ-AI/MiniMax-M2.7-JANG_4M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "JANGQ-AI/MiniMax-M2.7-JANG_4M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "JANGQ-AI/MiniMax-M2.7-JANG_4M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "JANGQ-AI/MiniMax-M2.7-JANG_4M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

⚠️ Requires MLX Studio to run. Standard mlx_lm cannot load mixed-precision JANG models. MLX Studio includes the JANG loader with automatic per-layer bit detection.

Follow us: X @dealignai

MiniMax-M2.7 JANG_4M

MiniMax M2.7 228B MoE — 4.06-bit mixed precision, 115 GB

The standard JANG profile — best quality-to-size ratio for Apple Silicon.

Recommended: Run in MLX Studio for best experience including thinking mode support and optimized MoE inference.

Important Settings

MiniMax M2.7 is an always-reasoning model. It thinks before answering on every prompt.

Setting	Value	Notes
Temperature	1.0	REQUIRED — greedy/temp=0 causes infinite thinking loops
Top P	0.95
Top K	40
Repetition Penalty	1.1	Optional, helps prevent loops

Model Details

Metric	Value
Source	`MiniMaxAI/MiniMax-M2.7` (FP8 E4M3)
Architecture	MoE (256 experts, top-8 active), GQA (48 heads / 8 KV), partial RoPE
Total Parameters	228.7B
Active Parameters	~1.4B per token
Profile	JANG_4M (CRITICAL=8-bit, IMPORTANT=4-bit, COMPRESS=4-bit)
Actual avg bits	4.06
Model size	115 GB
Format	JANG v2 (MLX-native safetensors, instant load)
group_size	128 (speed-optimized for 256 experts)
Routing	Sigmoid + bias correction (not softmax)
QK-norm	Full vector RMSNorm
Context	192K tokens

JANG_4M Bit Allocation

Tier	Components	Bits
CRITICAL	Attention (Q/K/V/O), lm_head	8
IMPORTANT	Embeddings	4
COMPRESS	Expert MLP (w1/w2/w3) — 98%+ of params	4
Passthrough	MoE router/gate (float16), norms, QK-norms	16

JANG protects routing and attention at full precision while compressing the 256 expert MLPs — where MoE models are most tolerant of quantization. The router is kept at float16 (no quantization) for maximum routing precision.

MMLU Comparison — All JANG Profiles (200q, reasoning ON)

Subject	JANG_2L (63 GB)	JANG_3L (89 GB)	JANG_4M (115 GB)	JANG_6M (167 GB)
Abstract Algebra	16/20	19/20	19/20	—
Anatomy	17/20	18/20	20/20	—
Astronomy	19/20	19/20	19/20	—
College CS	17/20	19/20	19/20	—
College Physics	16/20	20/20	20/20	—
HS Biology	19/20	20/20	19/20	—
HS Chemistry	16/20	19/20	19/20	—
HS Mathematics	18/20	20/20	20/20	—
Logical Fallacies	19/20	19/20	18/20	—
World Religions	19/20	18/20	18/20	—
TOTAL	176/200 (88.0%)	191/200 (95.5%)	191/200 (95.5%)	≥95.5%
GPU RAM	62.6 GB	88.6 GB	114.8 GB	167.2 GB

JANG_6M not benchmarked due to slow generation (~20 tok/s). Near-lossless 6-bit expected to match or exceed 4M/3L.

Why JANG for MiniMax

Standard MLX quantization on MiniMax produces completely broken output at ALL bit levels (~25% MMLU = random guessing). JANG's mixed-precision approach is the only working quantized MiniMax on Apple Silicon.

On M2.5, JANG_2L achieved 74% MMLU vs MLX's 25% (random). M2.7 results pending.

All Quantizations

Model	Profile	Size	Avg Bits
JANG_2L	(8, 6, 2)	63 GB	2.10
JANG_3L	(8, 4, 3)	89 GB	3.08
JANG_4M	(8, 4, 4)	115 GB	4.06
JANG_6M	(8, 6, 6)	167 GB	6.03

Requirements

Apple Silicon Mac with 128 GB unified memory
MLX framework
MLX Studio recommended

Tool Use / Agent Mode

MiniMax M2.7 uses interleaved thinking + tool calls — it reasons inside <think> blocks, then emits tool calls in <minimax:tool_call> format. Some clients (Opencode, etc.) may strip the <think> block and miss the tool call.

For tool-use clients, set enable_thinking=False in the chat template:

text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True,
    enable_thinking=False  # skips <think> injection for tool-use
)

MiniMax tool call format:

<minimax:tool_call>
<invoke name="tool_name">
<parameter name="param1">value1</parameter>
</invoke>
</minimax:tool_call>

Usage

from jang_tools.loader import load_jang_model
from mlx_lm import generate
from mlx_lm.sample_utils import make_sampler

model, tokenizer = load_jang_model("JANGQ-AI/MiniMax-M2.7-JANG_4M")
sampler = make_sampler(temp=1.0, top_p=0.95)

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "What is photosynthesis?"}],
    tokenize=False, add_generation_prompt=True
)
output = generate(model, tokenizer, prompt=prompt, max_tokens=2048, sampler=sampler)
print(output)

Support

MLX Studio | JANGQ | X @dealignai

Quantized by Jinho Jang (eric@jangq.ai) using JANG Tools v2.4.1.

This model is licensed under the MiniMax M2.7 Non-Commercial License. Commercial use requires prior written authorization from MiniMax (api@minimax.io). See LICENSE file for full terms.

Downloads last month: 520

Safetensors

Model size

33B params

Tensor type

U32

F16

MLX

Hardware compatibility

Quantized