93% MMLU at same size as MLX 4-bit. JANG_4M matches MLX 4-bit quality with 8-bit attention protection. Hybrid Mamba-2 SSM + Latent MoE + Attention.

LM Studio, Ollama, oMLX do NOT support JANG format. Use MLX Studio or `pip install "jang[mlx]>=2.1.5"`.

JANG is fully open-source. Quantization engine, research, and full commit history: github.com/jjang-ai/jangq. Created by Jinho Jang.

Key Features

• 93.0% MMLU (200 questions, reasoning mode) — matches MLX 4-bit at same size
• 55.1 tok/s generation, 154 tok/s prefill
• 63 GB on disk, 61.2 GB GPU RAM
• Reasoning mode: `...` step-by-step problem solving
• Hybrid architecture: 40 Mamba-2 SSM + 40 Latent MoE (512 experts) + 8 Dense Attention layers
• bfloat16 compute: auto-detected for 512-expert models

Results: JANG vs MLX (200-question MMLU)

Per-subject comparison. All models tested with and without reasoning using identical methodology.

Summary

JANG_4M nearly ties MLX 4-bit (93.0% vs 93.5%) at the same 63 GB size with 8-bit attention protection. MLX 3-bit cannot be created — `mlx_lm.convert` crashes on Nemotron's mtp.* weights. Only JANG can produce sub-4-bit quantizations.

Also see: JANG_2L (43 GB) — 20 GB smaller, fits 64 GB Macs, 75% no-think / 86% reasoning.

Specs

Requirements

• Apple Silicon Mac with 64+ GB unified memory
• MLX Studio or `pip install "jang[mlx]>=2.1.5"`

Quick Start

```bash pip install "jang[mlx]>=2.1.5" ```

```python from jang_tools.loader import load_jang_model from mlx_lm import generate

model, tokenizer = load_jang_model("JANGQ-AI/Nemotron-3-Super-120B-A12B-JANG_4M")

With reasoning

messages = [{"role": "user", "content": "Explain quantum computing."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True) result = generate(model, tokenizer, prompt=prompt, max_tokens=2048)

Without reasoning (faster)

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False) result = generate(model, tokenizer, prompt=prompt, max_tokens=100) ```

Technical Notes

• Latent MoE: Nemotron-H compresses hidden states 4096→1024 before expert routing. JANG loader handles this automatically.
• bfloat16: Auto-detected for 512-expert models. Prevents float16 overflow. Zero quality impact.
• trust_remote_code: Custom Python files included (modeling_nemotron_h.py, configuration_nemotron_h.py).

한국어

Nemotron-3-Super-120B JANG_4M — MLX 4-bit과 동일한 크기(63 GB)에서 93% MMLU 달성.

```bash pip install "jang[mlx]>=2.1.5" ```