Specifications
32K Context
Extended context window for long documents
Tool Calling
Native function calling support
Fine-tunable
TRL compatible (SFT, DPO, GRPO)
Quick Start
- Transformers
- llama.cpp
- vLLM
- SGLang
LFM2.5-1.2B-Instruct
Instruction-tuned 1.2B parameter model optimized for chat and general-purpose tasks
← Back to Text Models
LFM2.5-1.2B-Instruct is Liquid AI’s flagship instruction-tuned model, delivering exceptional performance for chat, instruction-following, and tool-calling tasks. Built on the LFM2.5 architecture with extended pre-training and reinforcement learning.
Was this page helpful?
⌘I