← all releases
Huawei·Nov 14, 2025·v1.0·open source

SINQ

SINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.

InfrastructureLLMsML
visit website
overview

SINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.

key features
  • 01Calibration-free quantization
  • 02Supports both symmetric and asymmetric quantization
  • 03NF4 support
  • 04Approximately twice as fast as HQQ
  • 05Higher model quality compared to alternatives
related productsbrowse all →
DetectFlowopen sourceDetectFlow is an open-source cybersecurity detection platform developed by SOC Prime. It leverages artificial intelligence to enhance the detection of cyber threats in real-time, enabling security operations teams to identify and respond to attacks more effectively.SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.Step-Audio-R1open sourceStep-Audio-R1 is an advanced audio language model developed by StepFun AI, designed to enhance audio reasoning capabilities by grounding its reasoning in acoustic features. It introduces Modality-Grounded Reasoning Distillation (MGRD), an iterative training framework that shifts the model's reasoning from textual abstractions to acoustic properties, effectively addressing the 'inverted scaling' problem where performance degrades with longer reasoning. This model has demonstrated superior performance across various audio understanding and reasoning benchmarks, surpassing models like Gemini 2.5 Pro and achieving results comparable to Gemini 3 Pro.