gemma-4-31B-it-JANG_5K

JANG adaptive mixed-precision MLX quantization produced via vmlx / jang-tools.

• Quantization: 5.15b avg, profile JANG_5K, method mse-all, calibration activations
• Profile: JANG_5K
• Format: JANG v2 MLX safetensors
• Compatible with: vmlx, MLX Studio, oMLX (with JANG patch)

Usage

vmlx (recommended)

pip install 'vmlx[jang]'
vmlx serve bearzi/gemma-4-31B-it-JANG_5K

Python

from jang_tools.loader import load_jang_model
from mlx_lm import generate

model, tokenizer = load_jang_model("bearzi/gemma-4-31B-it-JANG_5K")
messages = [{"role": "user", "content": "Hello"}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=True))

About JANG

JANG (Jang Adaptive N-bit Grading) assigns different bit widths to different layer types — attention layers get more bits, MLP/expert layers compress harder. This preserves model coherence at aggressive compression levels where uniform quantization breaks down.

See JANG documentation and scores at jangq.ai.

Comparative benchmarks and feedback welcome — please open a discussion.