jang 1.2.0

JANG — Adaptive Mixed-Precision Quantization for Apple Silicon. The GGUF equivalent for MLX.

Run JANG models with MLX Studio — the easiest way to run LLMs on Apple Silicon

---

Early Adoption: JANG is a new quantization format. LM Studio, Ollama, oMLX, and other MLX inference apps do not support JANG yet. Use MLX Studio (native JANG support) or the jang Python package for inference. Ask your favorite app's creators to add JANG support!

---

Jang Adaptive N-bit Grading

Mixed-Precision Quantization for Apple Silicon

The GGUF equivalent for MLX — models stay quantized in GPU memory at full Metal speed.

What is JANG?

JANG redistributes quantization bits based on tensor sensitivity. Critical layers (attention) get more bits, bulk layers (MLP) compensate — same total size, smarter allocation.

Like GGUF K-quants for MLX.

Results

2-bit: JANG doubles MLX on every model

Model	JANG_2S	MLX 2-bit	Size
Qwen3.5-122B MoE	84% MMLU	56%	38 GB vs 36 GB
Qwen3.5-35B MoE	62% MMLU	~20%	12 GB vs 10 GB
Qwen3.5-9B	36% MMLU	18%	3.5 GB vs 2.6 GB
Qwen3.5-4B	28% MMLU	14%	1.6 GB vs 1.3 GB

4-bit: JANG_4K — smaller than MLX, higher MMLU

Model	JANG_4K	MLX 4-bit	Size
Qwen3.5-35B MoE	84% MMLU	82%	16.7 GB vs 18 GB

Install

pip install jang

For inference on Apple Silicon:

pip install "jang[mlx]"

Quick Start

Convert any model

# K-quant 4-bit (budget-neutral, same size as MLX, smarter)
jang convert Qwen/Qwen3.5-35B-A3B -p 4

# 2-bit for extreme compression
jang convert Qwen/Qwen3.5-122B-A10B -p 2

# Specific profile
jang convert model -p JANG_2S

Run inference

from jang_tools.loader import load_jang_model
from mlx_lm.sample_utils import make_sampler
from mlx_lm.generate import generate_step
import mlx.core as mx

model, tokenizer = load_jang_model("JANGQ-AI/Qwen3.5-122B-A10B-JANG_2S")
sampler = make_sampler(temp=0.7)

tokens = tokenizer.encode("What is photosynthesis?")
for tok, _ in generate_step(prompt=mx.array(tokens), model=model, max_tokens=200, sampler=sampler):
    t = tok.item() if hasattr(tok, 'item') else int(tok)
    print(tokenizer.decode([t]), end="", flush=True)
    if t == tokenizer.eos_token_id:
        break

Profiles

Profile	Type	Bits	Best for
JANG_4K	K-quant	4.0	Same size as MLX 4-bit, smarter
JANG_3K	K-quant	3.0	Same size as MLX 3-bit, smarter
JANG_2S	Profile	~2.1	Tightest 2-bit, near MLX 2-bit size
JANG_2M	Profile	~2.1	Balanced 2-bit
JANG_2L	Profile	~2.3	Quality 2-bit
JANG_1L	Profile	~2.2	Maximum quality 2-bit

Pre-quantized Models

Available on HuggingFace:

Model	Profile	MMLU	Size
Qwen3.5-122B-A10B	JANG_2S	84%	38 GB
Qwen3.5-35B-A3B	JANG_4K	84%	16.7 GB
Qwen3.5-35B-A3B	JANG_2S	62%	12 GB

Supported Architectures

Dense Transformer, Mixture of Experts, Hybrid SSM, Linear Attention, MLA, Vision-Language, Mamba, FP8 source models.

Links

• GitHub | HuggingFace | MLX Studio | Format Spec

---

Created by Jinho Jang — jangq.ai