LFM 2.5 1.2B Thinking

Liquid

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.

Try Now

Capabilities

Thinking

Technical Specifications

Context Window

32,768 tokens

Max Output

32,768 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0

Non-Reasoning Output

$0

Legacy

Made legacy on

Reason

1.2B thinking model; too small for production

Recommended Replacement

Qwen3.6 Plus