LFM3

LFM3

Liquid AI
+
+

Related Products

  • LTX
    182 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Nexo
    18,780 Ratings
    Visit Website
  • AuctionMethod
    43 Ratings
    Visit Website
  • Google AI Studio
    41 Ratings
    Visit Website
  • Compute with Hivenet
    4 Ratings
    Visit Website
  • Google Cloud Speech-to-Text
    443 Ratings
    Visit Website
  • Mentornity
    99 Ratings
    Visit Website
  • Anaconda
    625 Ratings
    Visit Website
  • IUX
    968 Ratings
    Visit Website

About

LFM3 is Liquid AI’s family of compact, open-weight foundation models for text, vision, audio, and multimodal tasks. The release includes text-generation, vision-language, audio, omni, and decision-model variants. Developers can download the model weights, adapt supported models through fine-tuning, and run them locally on edge hardware or access them through Liquid AI’s hosted API. Use cases include conversational assistants, tool calling, speech transcription and generation, image and video understanding, document extraction, classification, routing, and robotics applications. LFM3 is intended for developers, researchers, and organizations building specialized AI applications that need flexible deployment choices, including local inference. Open-weight models are available under Liquid AI’s LFM Open License; commercial eligibility and terms depend on an organization’s annual revenue.

About

Qwen3.8-Flash-Next is an open-weight multimodal Mixture-of-Experts model and an early preview of the architecture planned for Qwen4. It systematically upgrades attention, residual connections, embeddings, and optimization to improve capability, computational efficiency, model capacity, and training stability. Its hybrid architecture combines Gated DeltaNet, which efficiently compresses historical information, with Qwen Sparse Attention, which selects important context at the micro-block level to reduce attention and indexing costs on long sequences. Gated Residual widens the residual stream into four branches and dynamically controls information flow across layers, while N-gram Embedding adds large-scale local-pattern memory with very little extra per-token computation and can be offloaded to host memory. The model uses a 125B-parameter main network plus 51B N-gram embedding parameters, while activating only 6B parameters per token.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Developers, AI researchers, and organizations building specialized AI applications, including applications using local or edge inference.

Audience

Developers, researchers, and AI teams seeking to run or study an efficient multimodal open-weight model with long-context reasoning, coding, multilingual, and agentic capabilities

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

$0.08/MTok
LFM3-1.7B API usage is $0.08 per million input tokens, $0.02 per million cached input tokens, and $0.20 per million output tokens. New organizations receive $2 in API credit. Open-weight models can be used in production free by developers, researchers, nonprofits, and businesses with less than $10 million in annual revenue; businesses above that threshold require a paid license.
Free Version Supported
Free Trial Not Supported

Pricing

$2 per 1M (input)
Free Version Not Supported
Free Trial Not Supported

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 Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Liquid AI
Founded: 2023
United States
www.liquid.ai/blog/lfm3

Company Information

Alibaba
Founded: 1999
China
qwen.ai/blog

Alternatives

Gemma 4

Gemma 4

Google

Alternatives

LFM2.5

LFM2.5

Liquid AI
Qwen3.5

Qwen3.5

Alibaba
GPT-6.1 Sol

GPT-6.1 Sol

OpenAI
Inkling

Inkling

Thinking Machines Lab
Qwen3.5

Qwen3.5

Alibaba
Qwen3.8-27B

Qwen3.8-27B

Alibaba

Categories

AI Coding Models Supported
AI Models Supported
Multimodal Models Supported

Categories

Integrations

Hugging Face Supported
Ollama Supported
Alibaba Cloud Not Supported
Alibaba Cloud Model Studio Not Supported
Cherry Studio Not Supported
Cline Not Supported
ClinePass Not Supported
Happy Shrimp 1.0 Not Supported
Hermes Agent Not Supported
LM Studio Supported
Model Context Protocol (MCP) Not Supported
ModelScope Not Supported
Novita AI Not Supported
OpenRouter Supported
Python Not Supported
Qwen Not Supported
Qwen Studio Not Supported
QwenCloud Not Supported
QwenWork Not Supported
vLLM Supported

Integrations

Hugging Face Supported
Ollama Supported
Alibaba Cloud Supported
Alibaba Cloud Model Studio Supported
Cherry Studio Supported
Cline Supported
ClinePass Supported
Happy Shrimp 1.0 Supported
Hermes Agent Supported
LM Studio Not Supported
Model Context Protocol (MCP) Supported
ModelScope Supported
Novita AI Supported
OpenRouter Not Supported
Python Supported
Qwen Supported
Qwen Studio Supported
QwenCloud Supported
QwenWork Supported
vLLM Not Supported
Claim LFM3 and update features and information
Claim LFM3 and update features and information
Claim Qwen3.8-Flash-Next and update features and information
Claim Qwen3.8-Flash-Next and update features and information