Embedl's Blog on Deep Learning
Hardware Aware Model Optimization
You probably hit a wall if you've ever trained a high-performing deep learning model and tried to deploy it to an embedd...
Agentic AI is Accelerating – But Can It Reach the Edge?
2025 is shaping up to be the year of agentic AI. Identified as one of the most transformative technology shifts on the h...
Llama 4 on the Edge: Overcoming Limitations of Deploying Mixture-of-Experts on Edge Devices
Introduction Mixture-of-Experts (MoE) has emerged as one of the most promising approaches for scaling up large generativ...
Google vs. OpenAI: New Breakthroughs in the AI Race – But at What Cost?
Since the release of ChatGPT in late 2022, OpenAI quickly established itself as the front-runner in the race for the mos...
Battle of the SLMs: Gemma vs LLama
The battle of the small language models (SLMs) just heated up with the release of the Gemma 3 models by the Gemma team a...
Deep Learning’s Sputnik Moment?
The DeepSeek Shock Shockwaves were sent around Silicon Valley and the stock market following the release of new AI model...
AI and UN Sustainability Goals: Reducing the Energy and Carbon Footprint of AI Models
The rapid expansion of Artificial Intelligence (AI) has revolutionized industries, yet its environmental implications ra...
ChatGPT in your lap: Bringing LLMs from the Cloud to the Edge
The wonderous ChatGPT continues to amaze – the new multimodal version could figure out that a picture was taken in Gothe...