LiquidAI: LFM2.5-1.2B-Thinking (free)
LFM2.5-1.2B-Thinking is a tiny free reasoning-oriented model from LiquidAI with very low benchmark scores across all areas — marginally stronger than its non-thinking sibling but still only suitable for the most basic experimental use.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is designed to provide higher-quality “thinking” responses in a small 1.2B model.
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 2B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
