Liquid AI’s cover photo
Liquid AI

Liquid AI

Information Services

Cambridge, Massachusetts 24,317 followers

We build efficient general-purpose AI at every scale.

About us

We build efficient general-purpose AI at every scale.

Industry
Information Services
Company size
51-200 employees
Headquarters
Cambridge, Massachusetts
Type
Privately Held
Founded
2023

Locations

Employees at Liquid AI

Updates

  • Introducing our new tiny vision model: LFM2-VL-3B 👀 Built for flexibility and performance: > 51.8% on MM-IFEval (instruction following) > 71.4% on RealWorldQA (real-world understanding)  > Excels in single and multi-image understanding and English OCR > Low object hallucination rate (POPE benchmark) > Expanded multilingual visual understanding: English, Japanese, French, Spanish, German, Italian, Portuguese, Arabic, Chinese, Korean This model expands our multimodal portfolio and demonstrates the universal applicability of our hybrid LFM2 backbones. Blog: https://lnkd.in/edFKrAJk HF: https://lnkd.in/eKrJizeA LEAP: https://lnkd.in/ePKp8CRx

    • No alternative text description for this image
  • Liquid AI reposted this

    🔥 LFM2-1.2B just got a major speed boost — 52 tokens/sec on Snapdragon X Elite. We’ve optimized Liquid AI’s hybrid LFM2-1.2B with our NexaML Turbo Engine, achieving real-time inference fully on the Qualcomm Hexagon NPU. LFM2’s new multiplicative-gate + convolution architecture isn’t trivial to run — it demanded hardware-aware graph optimization. NexaML Turbo squeezes every bit of NPU performance for faster, smoother on-device AI. This update shows what happens when great model design meets a purpose-built inference engine. Thrilled to be partnering with Liquid AI — and even more excited for what’s next. Ramin Hasani Mathias Lechner Alexander Amini Daniela Rus Jeffrey Li Manoj Khilnani Chun-Po Chang

  • Enjoy LFM2-1.2B on Qualcomm NPUs in NexaSDK! Special thanks to the Nexa AI for integrating a series of liquid instances.

    View organization page for Nexa AI

    5,483 followers

    LFM2-1.2B models from Liquid AI are now running on Qualcomm Hexagon NPU in NexaSDK, powered by NexaML engine. Four new edge-ready variants: - LFM2-1.2B — general chat and reasoning - LFM2-1.2B-RAG — retrieval-augmented local chat - LFM2-1.2B-Tool — structured tool calling and agent workflows - LFM2-1.2B-Extract — ultra-fast document parsing LFM2 is a brand-new hybrid model architecture with both transformers and the SSM. Most inference frameworks can’t even run it yet. NexaML can. That means these models now run fully accelerated on Qualcomm Hexagon NPUs, hitting real-time speeds with tiny memory footprints for popular edge intelligence tasks — perfect for phones, wearables, and edge devices. We’re already working with customers like Brilliant Labs on what this unlocks next in ARVR glasses. Model link in comments. And if you want to follow the new model drops, star NexaSDK — it helps us deliver faster! Manoj Khilnani, Chun-Po Chang, Dr. Vinesh Sukumar, Srinivasa Deevi, Devang Aggarwal, Madhura Chatterjee, Neeraj Pramod, Bobak Tavangar, Heeseon Lim, Justin Lee

  • View organization page for Liquid AI

    24,317 followers

    おはようございます!Liquid Nanosファミリーに新しく追加されたLFM2-350M-PII-Extract-JPを紹介します。  日本語テキストから個人情報(PII)を抽出し、 デバイス上での機密データのマスキングに使える構造化されたJSONを出力します。 データがローカル環境で処理されるため、プライバシーを保護したまま、クラウドモデル並みの精度と速度を実現します。 Huggingfaceモデル: https://lnkd.in/eD3Fi8tR  LEAPでのデプロイ: https://lnkd.in/eum9_3bm Liquidの最新情報はDiscordチャンネルで随時発信しています。ご参加をお待ちしています。https://lnkd.in/eShCjakY

    • No alternative text description for this image
  • View organization page for Liquid AI

    24,317 followers

    We have a new nano LFM that is on-par with GPT-5 on data extraction with 350M parameters. Introducing LFM2-350M-PII-Extract-JP 🇯🇵 Extracts personally identifiable information (PII) from Japanese text → returns structured JSON for on-device masking of sensitive data. Delivers the accuracy and speed of giant cloud-based models while keeping data where it belongs: fully private on-device. Download on HF: https://lnkd.in/eD3Fi8tR  Deploy with LEAP: https://lnkd.in/eum9_3bm Join our discord channel to get live-updates on latest from Liquid: https://lnkd.in/eShCjakY

    • No alternative text description for this image
  • Meet LFM2-8B-A1B, our first on-device Mixture-of-Experts (MoE)! 🐘 > LFM2-8B-A1B is the best on-device MoE in terms of both quality and speed. > Performance of a 3B-4B model class, with up to 5x faster inference profile on CPUs and GPUs. > Quantized variants fit comfortably on high-end phones, tablets, and laptops. Enabling fast, private, low-latency applications across modern phones, tablets, laptops, and embedded systems. Quality LFM2-8B-A1B has greater knowledge capacity than competitive models and is trained to provide quality inference across a variety of capabilities. Including: > Knowledge > Instruction following > Mathematics > Language translation Architecture   LFM2-8B-A1B is one of the first models to challenge the common belief that the MoE architecture is not effective at smaller parameter sizes. LFM2‑8B-A1B keeps the LFM2 fast backbone and introduces sparse MoE feed‑forward networks to add representational capacity without significantly increasing the active compute path. > LFM2 Backbone: 18 gated short convolution blocks and 6 GQA blocks.  > Size: 8.3B total parameters, 1.5B active parameters. > MoE placement: With the exception of the first two layers, all layers include an MoE block. The first two layers remain dense for stability purposes. > Expert granularity: 32 experts per MoE block, with top-4 active experts applied per token. This configuration provides a strong quality boost over lower granularity configs while maintaining fast routing and portable kernels. > Router: Normalized sigmoid gating with adaptive routing biases for better load balancing and training dynamics. CPU Performance: Across devices on CPU, LFM2-8B-A1B is considerably faster than the fastest variants of Qwen3-1.7B, IBM Granite 4.0, and others. GPU Performance: In addition to integrating LFM2-8B-A1B on llama.cpp and ExecuTorch to validate inference efficiency on CPU-only devices, we’ve also integrated the model into vLLM to deploy on GPU in both single-request and online batched settings. Our 8B LFM2 MoE model not only outperforms comparable size models on CPU but also excels against those same models on GPU (1xH100) with full CUDA-graph compilation during decode and piecewise CUDA-graph during prefill. Full Blog: https://lnkd.in/ecyCmKHM HF: https://lnkd.in/eKGCJEDk

    • No alternative text description for this image
  • Today, we expand our LFM2 family to audio. 👂👄 LFM2-Audio is an end-to-end audio-text omni foundation model, and delivers responsive, real-time conversation on-device at just 1.5B parameters. One model. Seamless multimodal support. No chains.  > Speech-to-speech > Speech-to-text > Text-to-speech > Audio classification  > Open weights 10x faster inference vs peers, with quality rivaling systems 10x larger. Efficiency: Efficiency is key for interactive real-time audio scenarios. LFM2-Audio-1.5B has an average end-to-end latency of under 100 ms, highlighting superb efficiency, even faster than models with much fewer than 1.5B parameters. Quality: LFM2-Audio-1.5B performs best-in-class by a large margin on conversational speech-to-speech chat – competitive with larger open models, such as Qwen2.5-Omni-3B (5B), Lyra-Base (9B), and GLM-4-Voice (9B). Model: LFM2-Audio is a novel omni-modal architecture that supports both text AND audio as first-class modalities, in both input and output. On the input side, the model intakes and tokenizes both text tokens and audio tokens into the same latent space. On the output side, the model autoregressively and flexibly generates tokens of either modality, depending on the task. Full Blog: https://lnkd.in/eHdbsAHg HF: https://lnkd.in/eJutwina

  • Liquid AI reposted this

    View profile for Pau Labarta Bajo
    Pau Labarta Bajo Pau Labarta Bajo is an Influencer

    Building and teaching AI that works > Maths Olympian> Father of 1.. sorry 2 kids

    Do you need helping building AI products/systems/apps/features 𝘁𝗵𝗮𝘁 𝘄𝗼𝗿𝗸? Let me help you ↓↓↓ This is my first week at Liquid AI, a frontier AI company with the most real-world and less BS goal I have found since 2023: "We help you build and deploy task-and-device optimized AI models for your use case" Yes, AI that runs wherever you need it to run: > laptops > phones > cars > robots > drones > smart home devices > Wherever. Liquid AI makes AI cheaper, faster, and data privacy friendly. GPT-<PLACEHOLDER> running on a remote data center is the opposite of all that. 𝗠𝘆 𝗿𝗼𝗹𝗲? TLDR: Help you my dear developer! I will be doing the same thing I have been doing for the last 3 years: I will show you how to build end-2-end projects using the open-weight models and open-source tools that we develop at Liquid AI. I will be talking to ALL OF YOU developers, both > LLM engineers and (super important!) > Devs that are non-LLM engineers who want to build AI powered apps, features and services. Because AI is a powerful technology that needs to be democratised, across - industries - deployment environments, and - developers 𝗗𝗼 𝘆𝗼𝘂 𝗻𝗲𝗲𝗱 𝗵𝗲𝗹𝗽? If you have interesting project ideas, or would like to collaborate on projects, please reach out to me. Feel free to send a DM on LinkedIn, or a comment on this post. Let's build real-world AI together!

    • No alternative text description for this image
  • Liquid AI reposted this

    View organization page for Liquid AI

    24,317 followers

    Today we announce a breakthrough in AI model training and customization that enables 350M–2.6B parameter foundation models (“Nanos”) to deliver GPT-4o-class performance on specialized agentic tasks—while running on phones, laptops, and embedded devices. In internal and partner evaluations, Liquid Nanos perform competitively with models up to hundreds of times larger. The result: planet-scale AI agents with cloud-free economics. “Liquid Nanos provide the task-specific performance of large frontier models at zero marginal inference cost. They are the ideal solution to generative AI applications with strict KPIs on response latency, inference cost, and privacy requirements,” said Mathias Lechner, Liquid AI CTO. Liquid’s task-specific Nanos are designed for the reality of most AI deployments. Their advantages include: > Purpose-built efficiency: Most AI use cases are task-specific, making smaller, fine-tuned models a natural fit. > Composable systems: Multiple Nanos can be combined to cover more complex use cases, while still being more efficient than a single 100B+ parameter, general-purpose model. > On-device deployment: Running models locally removes cloud dependencies, reducing costs and latency while keeping data private and secure. “Instead of shipping every token to a data center, we ship intelligence to the device. That unlocks private AI deployment with a cost profile that finally scales to everyone” said Ramin Hasani, Liquid AI CEO. By flipping the deployment model from the cloud to users’ devices, Nanos unlock real-time, performant, and private AI at up to 50x lower cost and 100x lower energy usage, enabling planet-scale AI agents with cloud-free economics. “I find it very impressive that Liquid's novel pre-training and post-training technique enables their fast and small LLMs to perform on par with frontier models such as GPT-4o, which is orders of magnitude larger, on specialized tasks," said Mikhail Parakhin, CTO, Shopify. "Liquid is simultaneously raising the bar for both performance and speed in foundation models, pushing beyond the state of the art. That is why we are excited to utilize their models across Shopify's platforms and services.” “Deloitte is excited about the opportunity to collaborate with Liquid AI and their new Nanos model, which has the potential to drive performance comparable to larger models at a lower cost,” said Ranjit Bawa, Chief Strategy and Technology Officer, Deloitte U.S. “Liquid’s Nanos represents a powerful inflection point for AI PCs, delivering frontier-level performance in a compact, energy-efficient form. At AMD, we share this focus on performance-per-watt leadership and see on-device intelligence as key to scaling AI broadly and sustainably,” said Mark Papermaster, CTO and EVP, AMD. Read more: https://lnkd.in/gfmE_b3H Available now on LEAP: https://lnkd.in/ekGFSJBA and HF: https://lnkd.in/eUWhnPpN

    • No alternative text description for this image

Similar pages

Browse jobs

Funding

Liquid AI 3 total rounds

Last Round

Series A

US$ 250.0M

See more info on crunchbase