IST-DASLab/Quartet-II
Quartet II Official Code
This project helps machine learning engineers and researchers optimize the pre-training process for large language models. It provides tools and kernels to train these models using NVFP4 precision, a more efficient format, while maintaining accuracy. The project takes existing large language model architectures and training data, and outputs a more efficiently trained model.
Use this if you are a machine learning engineer or researcher focused on pre-training large language models and want to reduce computational costs and memory footprint without sacrificing model accuracy.
Not ideal if you are looking for a high-level API for using pre-trained models or for training smaller, non-LLM machine learning models.
Stars
53
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IST-DASLab/Quartet-II"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bitsandbytes-foundation/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model...
dropbox/hqq
Official implementation of Half-Quadratic Quantization (HQQ)
OpenGVLab/OmniQuant
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
Hsu1023/DuQuant
[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger...