LFM2.5

LFM2.5

Liquid AI
+
+

Related Products

  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Google Cloud Speech-to-Text
    365 Ratings
    Visit Website
  • Google AI Studio
    26 Ratings
    Visit Website
  • Addigy
    261 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    967 Ratings
    Visit Website
  • ShareMyToolbox
    41 Ratings
    Visit Website
  • AdvancedMD
    2 Ratings
    Visit Website
  • Construction Daily Reports
    22 Ratings
    Visit Website
  • Label LIVE
    180 Ratings
    Visit Website
  • MobiOffice
    14,758 Ratings
    Visit Website

About

The Apple Foundation Models framework lets developers perform tasks with Apple’s on-device model that specializes in language understanding, structured output, and tool calling. It provides access to the on-device large language model that powers Apple Intelligence, helping apps perform intelligent tasks specific to their use case. The text-based on-device model identifies patterns that allow it to generate new text appropriate for the request, and it can make decisions to call code written by the developer to perform specialized tasks. Developers can generate text content for a wide range of tasks, including summarization, entity extraction, text understanding, refinement, dialog for games, creative content generation, classification, and more. It also supports guided generation, allowing developers to generate entire Swift data structures with strong guarantees by using the Generable macro.

About

Liquid AI’s LFM2.5 is the next generation of on-device AI foundation models designed to deliver high-performance, efficient AI inference on edge devices such as phones, laptops, vehicles, IoT systems, and embedded hardware without relying on cloud compute. It extends the previous LFM2 architecture by significantly increasing the pretraining scale and reinforcement learning stages, yielding a family of hybrid models around 1.2 billion parameters that balance instruction following, reasoning, and multimodal capabilities for real-world agentic use cases. The LFM2.5 family includes Base (for fine-tuning and customization), Instruct (general-purpose instruction-tuned), Japanese-optimized, Vision-Language, and Audio-Language variants, all optimized for fast, on-device inference under tight memory constraints and available as open-weight models deployable via frameworks like llama.cpp, MLX, vLLM, and ONNX.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Apple app developers who need to add private, on-device generative AI features with structured output and tool calling

Audience

Developers and organizations building on-device AI applications and intelligent agents that need efficient, high-quality AI models capable of running locally on consumer, edge, or embedded hardware

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

Free
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Apple
Founded: 1976
United States
developer.apple.com/documentation/FoundationModels

Company Information

Liquid AI
Founded: 2023
United States
www.liquid.ai/blog/introducing-lfm2-5-the-next-generation-of-on-device-ai

Alternatives

Silkwave Voice

Silkwave Voice

Silkwave

Alternatives

Aion 1.0 Plan

Aion 1.0 Plan

Microsoft
SmolLM2

SmolLM2

Hugging Face
HunyuanOCR

HunyuanOCR

Tencent
MedGemma

MedGemma

Google DeepMind
Qwen2

Qwen2

Alibaba

Categories

Categories

Integrations

Amazon Bedrock
ElevenLabs
Gemma 3
Gemma 4
Hugging Face
LEAP
Llama
Llama 3.2
Qwen3
Swift

Integrations

Amazon Bedrock
ElevenLabs
Gemma 3
Gemma 4
Hugging Face
LEAP
Llama
Llama 3.2
Qwen3
Swift
Claim Apple Foundation Models and update features and information
Claim Apple Foundation Models and update features and information
Claim LFM2.5 and update features and information
Claim LFM2.5 and update features and information