A double dose of agentic AI and model routing. See you. there!

In this new video, I introduce two new research-oriented models that Arcee.ai recently released on Hugging Face Face. Homunculus is a 12 billion-parameter instruction model distilled from Qwen3-235B onto the Mistral AI Nemo backbone. It was purpose-built to preserve Qwen’s

In this video, I introduce and demonstrate three production-grade models that Arcee.ai recently opened and released on Hugging Face . Arcee-SuperNova-v1 (70B) is a merged model built from multiple advanced training approaches. At its core is a distilled version of

In this fun demonstration, you can witness the impressive capabilities of Arcee.ai AFM-4.5B-Preview, Arcee's first foundation model, across diverse domains. The demo showcases the model tackling complex knowledge questions, creating sophisticated creative writing, and

This is what happens when I stay home for too long 🤣 In this 25-minute video, we take a deeeeep dive into Arcee.ai Fusion — a powerful new method for model merging that enables strong domain adaptation while preserving the base model’s original capabilities and knowledge. We

Curious about SLM inference on Intel, Graviton, and Qualcomm CPUs? Read on!

Arcee Conductor and Zerve: Bringing Model Routing to AI and Data Science Workflows x.com/i/broadcasts/1…

Ever been in a meeting thinking, “I should be taking notes, but I’m too busy actually participating”? Or worse, walked away with no idea what your next steps are? Indeed, commercial tools from Zoom , Microsoft , and others provide AI-powered companion features; however, they

Wow!

Good times yesterday at the MCP Conference in London (lu.ma/mcpconference). To cut through the hype, I demoed how to build single- and multi-agent MCP applications from scratch, using only open-source tools from Hugging Face (smolagents, Gradio) and Arcee.ai models

Small language models like Arcee.ai AFM-4.5B and Arm-based CPUs are a great match. My latest tutorial was just published on the Arm website. I'm walking you through setting up an Amazon Web Services Graviton4 instance, downloading and optimizing the model, running inference, and

"AI Regulation or AI Requiem?" - julsimon.substack.com/p/ai-regulatio… I've spent the last decade working across the AI landscape, first at AWS, then at Hugging Face, and now at Arcee AI. During this journey, I've traveled the world and witnessed very different philosophies about AI

Excited to partner with our Intel friends once again. Join us on August 12 to learn how enterprises can run advanced language models on Intel Xeon CPU, cutting costs, ensuring compliance, and maintaining full control. Info and registration at brighttalk.com/webcast/20283/…

Happy to share my new GitHub project: "An Amazon #SageMaker Container for Hugging Face Inference on AWS Graviton": github.com/juliensimon/sa… ✅ Based on a clean source build of llama.cpp ✅ Native integration with the SageMaker SDK and with Graviton3/Graviton4 instances ✅ Model

Our recent webinar with Intel is now available at brighttalk.com/webcast/20283/… In this session, you’ll learn how Arcee Foundation Models help decision makers to: • Achieve state-of-the-art AI performance optimized for Intel Xeon CPUs • Reduce the total cost of ownership by

Happy to partner with Amazon Web Services and looking forward to doing more together!

Small language models like Arcee.ai AFM-4.5B and Arm-based CPUs are a great match. My latest tutorial was just published on the Arm website. I'm walking you through setting up a Google Axion instance, downloading and optimizing the model, running inference, and evaluating