Qualcomm® AI HubAI Hub

LFM2.5-1.2B-Instruct

Compact 1.2B hybrid instruct model from Liquid AI built for on‑device deployment.

LFM2.5 is a family of hybrid language models from Liquid AI designed for fast, high‑quality on‑device deployment. The 1.2B Instruct model is tuned for instruction following, chat, and tool use.

View README
Not supported

This model is currently not supported on any IoT chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Model architecture:Hybrid architecture combining short-range gated convolutions with grouped-query attention (LFM2).
Response Rate:Rate of response generation after the first response token.
Supported languages:English, Arabic, Chinese, French, German, Japanese, Korean, Spanish

Applicable Scenarios

  • Dialogue
  • Content Generation

License

Model:LFM1.0
Terms of Use:Qualcomm® Generative AI usage and limitations

Tags

  • llm
  • generative-ai

Supported IoT Devices

  • Arduino VENTUNO Q
  • Dragonwing IQ-9075 EVK
  • Dragonwing Q-8750

Supported IoT Chipsets

  • Qualcomm® Dragonwing™ IQ-8275
  • Qualcomm® Dragonwing™ Q-8750
  • Qualcomm® Dragonwing™ IQ-9075

Related Models

See all models
View details for the Granite-4.0-Micro model.

Granite-4.0-Micro

Compact language model from IBM optimized for enterprise tasks.

View details for the Qwen3.5-2B model.

Qwen3.5-2B

Balanced 2B parameter model from the Qwen3.5 series for on-device inference.

Looking for more? See models created by industry leaders.

Discover Model Makers