Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Liquid AI's LFM2.5 represents an advanced iteration of on-device AI foundation models, engineered to provide high-efficiency and performance for AI inference on edge devices like smartphones, laptops, vehicles, IoT systems, and embedded hardware without the need for cloud computing resources. This new version builds upon the earlier LFM2 framework by greatly enhancing the scale of pretraining and the stages of reinforcement learning, resulting in a suite of hybrid models that boast around 1.2 billion parameters while effectively balancing instruction adherence, reasoning skills, and multimodal functionalities for practical applications. The LFM2.5 series comprises various models including Base (for fine-tuning and personalization), Instruct (designed for general-purpose instruction), Japanese-optimized, Vision-Language, and Audio-Language variants, all meticulously crafted for rapid on-device inference even with stringent memory limitations. These models are also made available as open-weight options, facilitating deployment through platforms such as llama.cpp, MLX, vLLM, and ONNX, thus ensuring versatility for developers. With these enhancements, LFM2.5 positions itself as a robust solution for diverse AI-driven tasks in real-world environments.
Description
On June 23, 2025, Microsoft unveiled Mu, an innovative 330-million-parameter encoder–decoder language model specifically crafted to enhance the agent experience within Windows environments by effectively translating natural language inquiries into function calls for Settings, all processed on-device via NPUs at a remarkable speed of over 100 tokens per second while ensuring impressive accuracy. By leveraging Phi Silica optimizations, Mu’s encoder–decoder design employs a fixed-length latent representation that significantly reduces both computational demands and memory usage, achieving a 47 percent reduction in first-token latency and a decoding speed that is 4.7 times greater on Qualcomm Hexagon NPUs when compared to other decoder-only models. Additionally, the model benefits from hardware-aware tuning techniques, which include a thoughtful 2/3–1/3 split of encoder and decoder parameters, shared weights for input and output embeddings, Dual LayerNorm, rotary positional embeddings, and grouped-query attention, allowing for swift inference rates exceeding 200 tokens per second on devices such as the Surface Laptop 7, along with sub-500 ms response times for settings-related queries. This combination of features positions Mu as a groundbreaking advancement in on-device language processing capabilities.
API Access
Has API
No
API Access
Has API
No
Integrations
Amazon Bedrock
Yes
ElevenLabs
Yes
Gemma 3
Yes
Gemma 4
Yes
Hugging Face
Yes
LEAP
Yes
Llama
Yes
Llama 3.2
Yes
Qwen3
Yes
Integrations
Amazon Bedrock
No
ElevenLabs
No
Gemma 3
No
Gemma 4
No
Hugging Face
No
LEAP
No
Llama
No
Llama 3.2
No
Qwen3
No
Pricing Details
Free
Free Trial
Yes
Free Version
Yes
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
Yes
iPad App
Yes
Android App
Yes
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
No
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
Yes
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
Yes
Vendor Details
Company Name
Liquid AI
Founded
2023
Country
United States
Website
www.liquid.ai/blog/introducing-lfm2-5-the-next-generation-of-on-device-ai
Vendor Details
Company Name
Microsoft
Founded
1975
Country
United States
Website
blogs.windows.com/windowsexperience/2025/06/23/introducing-mu-language-model-and-how-it-enabled-the-agent-in-windows-settings/