Models & Labs
Liquid AI releases efficient on-device agent model
Hugging Face Bloghigh confidence
Why it matters
- →Smaller MoE models can now compete with larger dense or MoE models in complex agentic benchmarks.
- →High token throughput on Apple Silicon makes real-time local agent interaction feasible for consumers.
- →Open weights and broad framework support lower the barrier to deploying private, reasoning-capable agents.
Liquid AI has released LFM2.5-24B-A2B, an open-weight mixture-of-experts model optimized for on-device agentic workflows. The model features a 131K context window and 2B active parameters per token, allowing it to outperform larger models like Qwen3.6-35B in tool-use benchmarks while maintaining high inference speeds on consumer hardware such as the Apple M5 Max. Available via Hugging Face with day-one support for major inference engines including vLLM and llama.cpp, the release targets developers seeking private, efficient local AI agents.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1MiniCPM5: A 1B Model for On-Device Projects
Sam Witteveen · July 5, 2026 · Related
- 2Scaling AI Agents with Redis Iris
Cole Medin · July 9, 2026 · Related
- 3Intel Explores Agentic AI for Enterprise Workflows
MIT Technology Review AI · July 27, 2026 · Related
- 4Together AI Enhances Model Inference Configuration
Together AI Blog · July 29, 2026 · Related
- 5Together AI Introduces Autoscaling for LLM Inference
Together AI Blog · July 31, 2026 · Related
- 6LFM2.5-2.6B: Efficient AI Agents for Local Deployment
Hugging Face Blog · August 4, 2026 · Same story
- 7OpenAI buys Macs for private AI agents
Wes Roth · September 1, 2026 · Related
- 8Jev: A Decision-Only AI Model for Agents
Cole Medin · September 21, 2026 · Related
What happened next
- 9Nvidia releases open Nemotron models for agents and PCs
TechCrunch AI · October 19, 2026 · Related
- 10Liquid AI releases LFM3 multimodal models
Hugging Face Blog · October 27, 2026 · Same story
- 11llama.cpp adds LiquidAI LFM3 model support
llama.cpp Releases · October 28, 2026 · Related
Follow this story
Open the full story →Liquid AI opens d1 decision models for edge inference
2 developments
- Oct 7 · Hugging Face Blog
Liquid AI opens d1 decision models for edge inference - Oct 13 · Hugging Face Blog
Liquid AI releases efficient on-device agent model (This article)↳ Liquid AI releases LFM2.5-24B-A2B, an efficient on-device agent model with 131K context that decodes at 184 tok/s on Apple M5 Max.
More from Hugging Face Blog
© Hugging Face BlogAgentsagents
NVIDIA Nemotron powers interactive Halloween agent
An NVIDIA engineer built a fully local voice agent for a Halloween attraction using the new Nemotron Voice Agent framework. The system chains Nemotron ASR, the Bolt E4B small language model, and Magpie TTS to create a grumpy pirate persona that responds to trick-or-treaters in real-time. Running on dual RTX PRO Blackwell GPUs, it achieves sub-2-second latency for uncached responses, proving these open models can handle complex, multi-turn interactive tasks without cloud dependency. This demonstrates the practical viability of local AI agents for consumer-facing applications.
Hugging Face Blog
© Hugging Face BlogModels & Labsmodels
Granite Switch 4.1.1 patches adapters without retraining base
IBM’s Granite Switch 4.1.1 proves modular architectures can move with the speed of standard software updates. By keeping the base model untouched and only updating specialized adapters like the multilingual ASR and decision logic, they sidestep the massive compute cost of full retraining. This approach lets developers compose new expertise on a single endpoint without migration headaches. It signals a shift toward composable AI where models evolve incrementally rather than in disruptive leaps.
Hugging Face Blog
© Hugging Face BlogGeneral AIresearch
Project ProtoStar launches to make public science AI-ready
Hugging Face and a coalition of major universities are launching Project ProtoStar to solve the 'last mile' problem of scientific data: making it machine-actionable. With $190 billion in annual U.S. federal R&D funding, the initiative pushes institutions like CMU and Purdue to release datasets in standardized formats rather than static files. The kickoff challenge tests AI's ability to predict urban climate conditions using historical weather records from 210 cities. This shifts the focus from mere publication to actual interoperability, creating a reusable infrastructure for AI-driven discovery.
Hugging Face Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe