Embedl AB

CES 2026! Join us at Eureka Park to discover how we help teams build faster, smarter, and more sustainable Edge AI solutions.

📍 Venetian Expo, Level 1, Hall G, Booth nr 60821

H200 GPU performance on an RTX 3500 - up to 500 tokens / s for 1B and 177 tokens / s for 3B SLMs.

Embedl is releasing the fastest SLMs on the planet with an architectural innovation that unlocks massive performance gains on Edge devices.

Sign up to be notified of the release next week: embedl.com/llm

If you are at EurIPS, come try the model out yourself and talk to Shahnawaz Ahmed, Hannes von Essen, and Wilhelm Tranheden at our booth!

🎄✨ Happy Holidays from Embedl! ✨🎄

As the end of 2024 approaches, we reflect on an incredible year filled with growth, collaboration, and innovation. We are grateful for our fantastic team, partners, and community who made this year so impactful.

Thank you for being part of our journey. We’re excited about what lies ahead in 2025 and can’t wait to continue achieving great things together.