← all releases
Liquid AI·Nov 25, 2025·v1.0·open source
LFM2.5-1.2B-Thinking
LFM2.5-1.2B-Thinking is a general-purpose text-only model designed for on-device deployment, building upon the LFM2 architecture with extended pre-training and reinforcement learning. It offers high-quality AI performance comparable to much larger models, optimized for efficient edge inference on various hardware platforms.
LLMs
overview
LFM2.5-1.2B-Thinking is a general-purpose text-only model designed for on-device deployment, building upon the LFM2 architecture with extended pre-training and reinforcement learning. It offers high-quality AI performance comparable to much larger models, optimized for efficient edge inference on various hardware platforms.
key features
- 011.17 billion parameters for robust performance
- 02Extended pre-training with 28 trillion tokens
- 03Context length of 32,768 tokens for handling extensive inputs
- 04Supports multiple languages including English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish
- 05Optimized for fast inference on CPUs, GPUs, and NPUs
related productsbrowse all →
Protenixopen sourceProtenix is an open-source, trainable PyTorch implementation of AlphaFold 3, designed for high-accuracy biomolecular structure prediction. It aims to advance accessible and extensible research tools for the computational biology community. ([github.com](https://github.com/bytedance/Protenix?utm_source=openai))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.SINQopen sourceSINQ (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.