---
license: other
license_name: minimax-open
library_name: mlx
tags:
- mlx
- jang
- minimax
- moe
- apple-silicon
pipeline_tag: text-generation
---

<p align="center">
  <img src="mlx-studio-logo.png" alt="MLX Studio" width="400"/>
</p>

<p align="center">
  <img src="jangq-logo.png" alt="JANGQ" width="200"/>
</p>

<div align="center">

# MiniMax-M2.7 JANG_6M

**MiniMax M2.7 228B MoE — 6.03-bit mixed precision, 167 GB**

Near-lossless quantization for maximum quality on Apple Silicon.
</div>

> **Recommended: Run in [MLX Studio](https://mlxstudio.com)** 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_6M (CRITICAL=8-bit, IMPORTANT=6-bit, COMPRESS=6-bit) |
| Actual avg bits | 6.03 |
| Model size | 167 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_6M Bit Allocation

| Tier | Components | Bits |
|------|-----------|------|
| CRITICAL | Attention (Q/K/V/O), lm_head | 8 |
| IMPORTANT | Embeddings | 6 |
| COMPRESS | Expert MLP (w1/w2/w3) — 98%+ of params | 6 |
| 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 Benchmarks (200q, 10 subjects, reasoning ON)

*Coming soon — benchmarks in progress.*

## 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](https://huggingface.co/JANGQ-AI/MiniMax-M2.7-JANG_2L) | (8, 6, 2) | 63 GB | 2.10 |
| [JANG_3L](https://huggingface.co/JANGQ-AI/MiniMax-M2.7-JANG_3L) | (8, 4, 3) | 89 GB | 3.08 |
| [JANG_4M](https://huggingface.co/JANGQ-AI/MiniMax-M2.7-JANG_4M) | (8, 4, 4) | 115 GB | 4.06 |
| [JANG_6M](https://huggingface.co/JANGQ-AI/MiniMax-M2.7-JANG_6M) | (8, 6, 6) | 167 GB | 6.03 |

## Requirements

- Apple Silicon Mac with 192 GB unified memory
- MLX framework
- [MLX Studio](https://mlxstudio.com) 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:

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

## Usage

```python
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_6M")
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](https://mlxstudio.com) | [JANGQ](https://jangq.ai) | [X @dealignai](https://x.com/dealignai)

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

---

*This model is provided for research and personal use. Users are responsible for ensuring their use complies with applicable laws and the MiniMax license.*