LFM2.5-1.2B-mobile

LFM2.5-1.2B-Instruct

This model is intended to be used with NexaSDK for deploying on Snapdragon 8 Gen 4 NPU. Follow the instructions here to get started.

Model Description

LFM2.5-1.2B-Instruct is a 1.2B-parameter instruction-tuned language model designed for strong capability at small scale and efficient on-device/edge deployment.

It builds on the LFM2 architecture (introduced July 2025) and improves performance by extending pretraining from 10T → 28T tokens and scaling post-training with reinforcement learning, targeting better instruction following and general usefulness in real-world tasks.

Features

• Instruction following: reliable responses to natural-language tasks and multi-step requests.
• Reasoning & analysis: structured problem solving and coherent explanations at ~1B scale.
• Content generation: summaries, drafts, rephrasing, and structured outputs.
• Efficient deployment: optimized for practical inference in resource-constrained environments.

Use Cases

• On-device assistants (mobile, PC, IoT, automotive)
• Chatbots and customer support automation
• Document summarization, rewriting, and analysis
• Education and tutoring (Q&A, step-by-step explanations)
• Developer workflows (notes, lightweight coding help, documentation drafts)

Inputs and Outputs

Input:

• Text prompts or conversation history (tokenized sequences for APIs).

Output:

• Generated text (answers, explanations, summaries, and structured content).
• Optionally, raw logits/probabilities for advanced tasks.

License

This repo is licensed under the Creative Commons Attribution–NonCommercial 4.0 (CC BY-NC 4.0) license, which allows use, sharing, and modification only for non-commercial purposes with proper attribution. All NPU-related models, runtimes, and code in this project are protected under this non-commercial license and cannot be used in any commercial or revenue-generating applications. Commercial licensing or enterprise usage requires a separate agreement. For inquiries, please contact [email protected]