SuperNova-v1 70B, Virtuoso-Large 72B, Caller 32B, GLM-4-32B-Base-32K, and Homunculus 12B
Optimizing AI workflows for enhanced precision, performance, and cost efficiency.
Model routing for the win!
Merging for pre-training, data privacy in healthcare, and language support
Aggressive experimentation, model merging, distillation, and a concerning amount of soup.
Prosperity7VC, M12, Hitachi Ventures, JC2, Wipro, Samsung, and Guidepoint are now backing Arcee AI.
Built for performance, compliance, and affordability.
The first release—AFM-4.5B—is a 4.5-billion-parameter model that delivers excellent accuracy, strict compliance, and very high cost-efficiency.
A training-free method to transplant tokenizers in pre-trained language models
With a chatbot interface powered by open-source small language models and real-time data analytics, store associates can interact through voice or text.
How Arcee AI helped Madeline build a reasoning model from first principles.
Discover Arcee AI's suite of small language models, now available on Together.ai and OpenRouter for fast, cost-efficient AI applications.
Learn how Arcee Conductor enriches inventory data with human-readable descriptions, improves searchability, and reduces costs by up to 75%.
Discover Auto Reasoning, Arcee Conductor’s new feature that intelligently routes complex prompts to the best reasoning model. Learn how Maestro excels at multi-step problem solving and why advanced reasoning is critical for modern businesses.
Today we're excited to announce a new "Auto Tools" feature in our intelligent model routing solution, Arcee Conductor. Auto Tools routes your tool calling / function calling prompts to the optimal model–selecting only from models specialized in tool calling.
Despite the buzz that "SEO is dead," SEO is more vital than ever in the AI era. Learn how AI is reshaping SEO and get actionable tips to stay ahead in search and content strategy.
Chatbot vs. Agentic AI: which is right for your business? Understand the key differences, use cases, and decision points to choose the best automation solution.
Manual claims are slow and costly. Discover how enterprise leaders can implement automated insurance claims processing effectively with this guide on application and success measurement.
Move beyond theory: learn how AI sales agents are transforming sales workflows. See concrete examples in lead gen, outreach, and AI-powered calls–and understand their strategic impact.
Transform knowledge management with AI. Learn how AI knowledge bases save time, reduce costs, and enhance satisfaction by delivering dynamic, accessible information.
Tired of manual recruitment tasks? Learn how AI agents automate candidate sourcing, resume evaluation, and interviews–significantly reducing time-to-hire and improving efficiency.
We break down the reactions to the LLama 4 release–analyzing the missteps but also highlighting strengths that may have been overlooked amidst the initial noise.
Our Chief Evangelist, Julien Simon, explores the advantages and practical applications of running SLM inference on Arm CPUs.
Learn how AI model routing solves key challenges in AI adoption by cutting costs, improving performance, and simplifying model selection. Discover how businesses use routing to deploy the right model for every task.
Explore how AI research agents revolutionize enterprise research by automating market analysis, competitor tracking, and sentiment insights.
Learn what virtual agents are, how they differ from AI agents, and how businesses use them to automate customer support, cut costs, and scale efficiently.
Discover how agent assist can boost customer service efficiency with real-time AI support. Get faster resolutions, lower costs, and happier customers. Learn key benefits, top alternatives, and how to choose the right AI solution for your business.
Are you sending all of your prompts to a single LLM? We've heard from many companies and individual users that they don't have time to constantly evaluate which model to use for each of their use cases. That's why we built Arcee Conductor, an intelligent model router that transforms your AI experience by ensuring you always get superior results at the lowest possible cost – and always tailored to each unique prompt or query.
Facing growing, unpredictable AI budgets? Arcee Conductor intelligently routes prompts to the optimal AI model based on complexity, cutting costs by up to 99% per prompt without sacrificing quality. Beyond a simple LLM router, it offers a comprehensive catalog of both SLMs and LLMs.
For mid-market and enterprise leaders, the key to automation is implementing it for maximum impact. Intelligent automation can drive annual savings of up to 40% and cut process times by 70%. This guide explores what intelligent process automation is, how it differs from traditional methods, and whether it’s the right fit for your business.
Discover how AI marketing agents revolutionize enterprise marketing by analyzing data, making real-time decisions, and automating tasks to scale smarter. Learn how they enhance, not replace, your team to drive efficiency and impact.
Discover the key differences between traditional automation and AI agents in 2025. Learn how businesses are leveraging AI-driven workflows to enhance efficiency, decision-making, and adaptability. Find out which approach, rules-based automation or AI-powered automation, is the right fit for your business strategy.
Why does the model or (models) used in your agentic AI workflows matter? In this article we explain why the choice of models is key to a successful agentic AI strategy, and why small language models (SLMs) are an ideal solution.
Today we bring you exciting updates on two small language models (SLMs) we've been working on: our first reasoning model, Arcee-Maestro-7B-Preview, and a fast and efficient Mistral-based DeepSeek distillation we call Arcee-Blitz.
With Arcee Orchestra, you’ll transform complexity into simplicity, see faster collaboration across departments, and ultimately drive business growth—one automated workflow at a time.
MergeKit changed the game when it came to model merging, and today we're excited to bring you some game-changing updates to MergeKit–with what we're calling MergeKit v0.1. Starting today, you'll be able to unlock the power of model merging more than ever, with enterprise hosting, premium features, and expert support.
Discover how knowledge distillation makes AI models faster, more efficient, and cost-effective without sacrificing performance. Learn how Arcee AI leverages this technique to optimize models like Virtuoso Lite and Virtuoso-Medium-v2, delivering powerful AI solutions with lower computational demands. Explore the benefits, use cases, and how your organization can implement knowledge distillation to scale AI performance while reducing costs.
Here at Arcee AI, we're going beyond the hype and speculation surrounding the DeepSeek R-1 release. We're doing what we always do: working hard on training models. Soon we will deliver you distillations of R-1, and in the meantime, we're bringing you two distilled versions (10B, 32B) of DeepSeek-V3.
Enhance customer experience with AI-powered solutions that personalize interactions, anticipate needs, and automate support. Discover how AI agents, chatbots, and predictive analytics improve response times, streamline operations, and boost customer satisfaction. Learn how businesses leverage AI to transform CX and deliver seamless, proactive customer journeys.
Discover how AI-powered digital agents redefine automation by streamlining workflows, providing personalized customer service, and enabling predictive maintenance. Explore the future of intelligent, adaptive systems that operate seamlessly in dynamic environments.
Discover how AI agent builders can transform your business in 2025. This article explores what AI agent builders are, their benefits, top platforms, and tips for choosing the right one for your organization. Stay ahead in the AI revolution!
We all know that large language models (LLMs) power many of the most well-known AI tools–but are they the ideal solution for enterprises, which face challenges like handling sensitive data, integrating with complex systems, and ensuring that solutions provide relevant and up-to-date information tailored to specific industries? We take a closer look, and show that enterprise LLMs AND small language models (SLMs) can be customized and scaled so that businesses can implement the most cutting-edge AI.
Explore the immense capabilities of large language models (LLMs) like GPT-4 and PaLM, which leverage vast datasets and billions of parameters to generate human-like language, solve complex tasks, and drive diverse AI applications.
AI agents are the big AI trend this year, with a growing number of companies getting them into production. Check out our article to learn everything you need to know about getting started with building them and quickly getting ROI.
Arcee AI and Intel Gaudi2 make for a powerful combination when it comes to advancing financial insights via LLMs. Learn how the Arcee AI team used Intel's Habana Gaudi2 technology to train two advanced models with 10 billion tokens of financial data, leading to nuanced insights for analysts, investors, and other stakeholders.
Learn how we're leveraging small language models (SLMs) to power agentic AI workflows, in our new end-to-end, easy-to-use platform called Arcee Orchestra.
First, we pioneered small language models (SLMs). Now, we're elevating them to their full potential, leveraging them in our end-to-end, easy-to-use agentic AI workflow platform called Arcee Orchestra. Here's a look at how we got started with SLMs, and how we're now taking them to the next level.
Get direct access to the small language models (SLMs) that power Arcee Orchestra, our new end-to-end, SLM-powered agentic AI platform. Sign up for the public beta of the Arcee Model Engine today.
AI is transforming healthcare by optimizing clinical workflows, reducing inefficiencies, and improving patient outcomes. Learn how AI tools like Arcee Orchestra streamline care delivery and decision-making.
There's no doubt in our mind that 2025 will be the year of AI agents: many companies have already starting implementing them, and a growing number of AI providers are offering a variety of agents. Here's your primer on what you ned to know to get started.
Discover how enterprise automation can revolutionize your workflows, boost efficiency, and reduce costs. Learn about the latest strategies and tools, with real-world examples.
The Arcee AI research team is honored to be among the contributors to the world's first fully decentralized training of a large language model (LLM). Read about the game-changing project led by Prime Intellect, and how we brought our expertise to the post-training.
How can you use AI to deliver real business results fast? As we head into 2025, Generative AI alone won't cut it. Learn about how adding AI agents to your strategy is the new key to getting ROI from your AI.
As we approach the end of 2024, it's clear that the rise of small language models (SLMs) has been one of the defining developments in AI this year. For those of you still stuck in LLM-world, here's a crash course on SLMs.
Today Arcee AI makes our latest contribution to AI in underserved global languages with the release of a 3B Vietnamese SLM, Arcee-VyLinh.
Hot on the heels of our top-performing 72B Arabic-language model Arcee-Meraj, we bring you a 7B version: Arcee-Mini-Meraj, which boasts exceptional performance in instruction-following, generating long texts, structured data understanding, and generating structured outputs.
In the 2024 McKinsey Global Survey on generative AI, 65% of respondents reported that their organizations regularly use GenAI. The adoption has nearly doubled in less than a year. You’re most likely using generative AI personally or in your company for everything from straightforward tasks like getting help writing
First came our flagship 70B SuperNova, followed by the 8B SuperNova-Lite. Today we add to this family of superpower Small Language Models with the release of the 14B SuperNova-Medius.
Meet Arcee-SuperNova: a groundbreaking model with state-of-the-art abilities in instruction-following and strong alignment with human preferences.
We trained Arcee SuperNova-70B and Arcee SuperNova-8B to be a generally intelligent Llama-3.1-405B derivatives using intelligent distillation, novel post-training, and model merging techniques.
Artificial intelligence (AI) has become a fundamental part of business innovation across industries. The potential for AI software is huge—from automating mundane tasks to generating insights that drive strategic decisions. Yet, despite its growing importance, you might hesitate to implement AI solutions in your company. And it’s most
A growing number of enterprises are realizing that the cost of Generative AI can be exorbitant. This article looks at why the price can be so high and unpredictable, and offers advice on how to implement GenAI with a cost-effective approach.
Artificial Intelligence (AI) enables businesses to solve complex problems faster than ever. However, as decision-makers consider implementing AI solutions, one key question arises: How much energy does AI actually consume? The answer is not straightforward. AI's energy usage depends on factors that include:* The size of the model* The infrastructure
We've taken our groundbreaking general-purpose model, Arcee Nova, and enhanced it for Arabic – leading to an Arabic-language LLM that's enterprise-ready, with unprecedented text-generation and comprehension capabilities.
Companies are becoming increasingly aware of the potential business value of open source large language models, which are quickly approaching the performance of their closed source counterparts.
Get ready for a game-changer when it comes to AI for complex problem-solving & decision making, with Arcee AI's Mixture of Agents architecture release: Arcee Swarm. Rather than relying on one LLM to handle all tasks, Arcee Swarm routes your query to a collection of smaller expert models.
Direct Preference Optimization (DPO) is one of the top methods for fine-tuning LLMs... It's available on our model training platform - and today, we bring you support for DPO on our training APIs.
Coming on the heels of Arcee-Spark – our incredibly performant 7B model – we now bring you Llama-Spark. Built on Llama-3.1-8B, Llama-Spark is a conversational AI that you'd never suspect is just an 8B parameter model.
How much do you know about Large Language Models (LLMs), the tech behind AI-powered assistants? We give you the basics on both open source and closed source LLMs.
Read the DistillKit v0.1 by Arcee AI Technical Paper: our new open-source tool that's set to change how we create and distribute Small Language Models (SLMs).
Arcee.ai is thrilled to announce the release of DistillKit, our new open-source tool that's set to change how we all create and distribute Small Language Models (SLMs).
Get Llama-3.1 but better – customize the OS model for all your needs, using Arcee AI's training, merging, and adaptation techniques and tools. Our team created this guide to get you started.
Joint customers use MongoDB & Arcee AI to take data from JSON files and turn it into world-class custom language models with practical business use cases–in just a few clicks.
Today, we have made two important datasets publicly available: 1. Agent Data: This dataset was instrumental in training Arcee-Agent. It contains Salesforce-xlam, agent-flan, and a custom version of Glaive-FC2 with 20k extended samples that call for the model to do tool use sequentially within the same response, along with Magpie-Pro
What a week here at Arcee AI. On the heels of Arcee-Scribe yesterday, today we bring you Arcee-Nova – our highest-performing open source model... Evaluated on the same stack as the OpenLLM Leaderboard 2.0, making it the top-performing open source model tested on that stack. Its performance approaches that of
Less than a year after emerging from stealth, Arcee AI has hit the headlines – announcing a major Series A, the arrival of Chief Evangelist Julien Simon, and the launch of a new cloud platform.
Need a guide or some inspiration for your writing tasks–especially those that require a bit of creativity? Check out Arcee-Scribe by Arcee AI.
Here at Arcee AI, we're the pioneers of training performant and efficient LLMs with Model Merging... And now we bring you *yet another* cutting-edge technique that also dramatically optimizes your training and improves your models.
So you want to train a custom language model, and you do have the requisite large set of text data. But how do you know that the data is *really actually ready* for model training? Our researchers here at Arcee AI tell you what to look out for.
Arcee Agent is yet another Arcee model punching above its weight: it's just 7B (initialized from Qwen2-7B) and outranks much larger models. Try it out for function calling and tool use!
Adapting an LLM to a specific domain might sound straightforward, but it in fact opens a Pandora's box of challenges. Our research team explains the shortfalls of some of the most common techniques.
Looking for proof that Small is the new Big when it comes to language models? Look no further than the model we've just dropped here at Arcee AI: you get top-notch results with just 7B parameters.
We built Llama-3-SEC upon the powerful Meta-Llama-3-70B-Instruct model, with the goal of providing unparalleled insights and analysis capabilities for financial professionals, investors, researchers, and anyone working with SEC filings and related financial data.
We're thrilled to announce that we’re launching Arcee Cloud, a fully hosted SaaS offering that makes world-class LLM production accessible to all – in an easy-to-use platform for Training, Merging, and Deploying custom language models.
We show you how to use Arcee's MergeKit to extract LoRA adapters from fine-tuned models, then leverage the Hugging Face Hub to create a library of general and task-specific LoRA adapters.
We've been focused on developing this groundbreaking technique for the community, and we're now excited to announce the launch of this state-of-the-art functionality in MergeKit.
Arcee's research shows that the Standard Continual Pre-Training (CPT) approach performs better than QLORA-based CPT.
And what do we do at Arcee when an exciting new model drops? We MERGE IT on MergeKit! We walk you through the process and share the initial results.
Arcee & MergeKit advance model merging innovations with launch of MergeKit Hackathon, co-sponsored by AWS. Submit your model merging research, experiments, and results for the chance to win cash prizes!
Check out our new Model-Tools repository on Github: a collection of custom tools, scripts and more to boost your LLMOps capabilities.
It’s the place to be for anyone who wants to learn about the next big thing in LLMs: The SMALL Language Show, live-streaming biweekly and bringing you chats with the world's top experts in LLM and SLM research.
We show how Arcee uses the most innovative Continual Pre-Training and Model Merging techniques to deliver high-quality domain-specific language models at a fraction of the cost of our competitors–using Medical and Patent data.
LLMs are so 2023, and SLMs (Small Language Models) are the future of enterprise GenAI. Our Solutions Engineering Lead Tyler Odenthal wrote about how domain-adapted SLMs are being used across diverse sectors ranging from law and healthcare to education and customer service.
The first quarter of 2024 isn’t over yet, but we’ve already had epic developments at Arcee – with TechCrunch announcing our seed round, and our decision to merge with mergekit.
On Day 3 of March Merge Madness we’re striking a bit of a serious note, with a discussion about our very serious commitment to the open source community.
Why the state-of-the-art technique works so well for our Small Language Model (SLM) system and domain-specific tasks
To celebrate Arcee’s recent merger with mergekit, we’re bringing you a month of resources and knowledge on model merging.
Arcee's recent merger with mergekit has made us a leader in model merging research and development. Check out our video interview with mergekit Founder Charles Goddard, who's come onboard our team as a Senior Research Engineer.
When it comes to the world of language models and Gen AI, a key question for companies looking to adopt these innovations is which model(s) to use. As if it’s not already complicated enough with the plethora of foundational models out there, it is now even more daunting
At Arcee, we believe in a world of smaller, specialized models that we call SLM’s. The “S” stands for smaller, specialized, scalable, and secure. These models are grounded on your data, run entirely in your own environment, and are infinitely scalable for all your use cases.