LFM2Liquid AI
|
||||||
Related Products
|
||||||
About
LFM2 is a next-generation series of on-device foundation models built to deliver the fastest generative-AI experience across a wide range of endpoints. It employs a new hybrid architecture that achieves up to 2x faster decode and prefill performance than comparable models, and up to 3x improvements in training efficiency compared to the previous generation. These models strike an optimal balance of quality, latency, and memory for deployment on embedded systems, allowing real-time, on-device AI across smartphones, laptops, vehicles, wearables, and other endpoints, enabling millisecond inference, device resilience, and full data sovereignty. Available in three dense checkpoints (0.35 B, 0.7 B, and 1.2 B parameters), LFM2 demonstrates benchmark performance that outperforms similarly sized models in tasks such as knowledge recall, mathematics, multilingual instruction-following, and conversational dialogue evaluations.
|
About
distil labs optimizes AI workloads by replacing expensive frontier-model calls with custom small language models tuned to a specific task while maintaining the required quality bar. It observes real production traffic, captures traces from existing LLM requests, and automatically builds an evaluation set to understand how the workload actually behaves. It then generates and validates synthetic training data, matches the data distribution to the target workload, performs supervised fine-tuning and reinforcement learning, quantizes the model, and deploys an optimized endpoint. Results are automatically evaluated against the current model on accuracy, latency, and efficiency before teams choose to scale traffic. The resulting OpenAI-compatible endpoint combines a specialized SLM, prompt optimization, caching, and tuned serving for the use case.
|
|||||
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
Developers and engineering teams needing a solution offering foundation models without reliance on cloud infrastructure
|
Audience
AI product, engineering, and machine learning teams in need of a tool to optimize production LLM workloads with task-specific small language models
|
|||||
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
No information available.
Free Version
Free Trial
|
Pricing
$0.04 per 1M tokens
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationLiquid AI
Founded: 2023
United States
www.liquid.ai/blog/liquid-foundation-models-v2-our-second-series-of-generative-ai-models
|
Company Informationdistil labs
Founded: 2024
Germany
www.distillabs.ai/
|
|||||
Alternatives |
AlternativesNo Alternatives
|
|||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
GPT-5.4 nano
Gemini 2.0 Flash-Lite
Hugging Face
OpenAI
OpenRouter
Qwen3
Together AI
|
Integrations
GPT-5.4 nano
Gemini 2.0 Flash-Lite
Hugging Face
OpenAI
OpenRouter
Qwen3
Together AI
|
|||||
|
|
|