WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Localized Open Models in Production: What Builders Need to Know

Ankit Patel , Pierre-Louis Cedoz , Jamie Madden , Stephen Batifol

A less capable model with a highly engineered workflow consistently outperforms a massive frontier model. Learn how to quantize weights and deploy enterprise-ready, localized AI on standard hardware.

Pause
Mute Enter Fullscreen
#1 about 2 min

Defining local open AI models for production environments

Owning and executing model weights directly differentiates local deployment from standard cloud provider APIs.

#2 about 2 min

Leveraging quantization techniques to scale local hardware execution

Compressing models with advanced quantization formats like FP4 enables massive parameter sets on consumer GPUs.

#3 about 4 min

Implementing enterprise governance and logging for multi-agent workflows

Capturing comprehensive system logs and human-in-the-loop approvals satisfies strict compliance and workflow auditing requirements.

#4 about 2 min

Defining execution environments for browser and computer use agents

Providing secure desktop or web sandboxes mitigates risk when computer-use agents interact with unstructured environments.

#5 about 5 min

Evaluating subjective generative media with artificial and human judges

Combining vision-language model scoring with manual oversight bridges the difficulty of evaluating nuanced aesthetic outputs.

#6 about 4 min

Optimizing execution costs and inference speeds with localized endpoints

Post-training smaller deterministic models for localized execution prevents escalating API costs and excessive inference latency.

#7 about 5 min

Automating workloads using scheduled agents and continuous model fine-tuning

Deploying long-running background agents to retrieve data and refine models eliminates tedious infrastructure management tasks.

#8 about 3 min

Combating workflow drift and integrating underlying infrastructure updates

Consistently auditing agent outputs and applying underlying driver enhancements guarantees long-term reliability and compounded performance gains.

#9 about 5 min

Prototyping multi-step workflows quickly within accessible model playgrounds

Verifying foundational model capabilities in web-based playgrounds prevents wasted engineering effort on overly complex workflow harnesses.

#10 about 3 min

Simulating physics and complex realities using emergent world models

Deploying architectures that intrinsically understand physical logic drives advanced video simulation and autonomous robotic control.

Matching moments

2:17 min

Transitioning generative AI from experimentation to production

Adolf Hohl Adolf Hohl · WWC 2024

1:32 min

Constructing scalable AI factory stack blueprint architectures

Anshul Jindal Anshul Jindal +1 · WWC Europe 2026

2:02 min

Shifting focus from isolated models to enterprise AI systems

Mohak Chadha Mohak Chadha · WWC Europe 2026

1:09 min

Deploying algorithms and AI models to edge production

Irina Terekhova Irina Terekhova · WWC Europe 2026

1:48 min

Identifying barriers to enterprise generative AI production environments

Stephan Gillich Stephan Gillich · WWC 2024

4:44 min

Introduction to prototyping and building practical AI applications

Krzysztof Cieślak Krzysztof Cieślak · WWC 2024

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 1 month ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
about 1 month ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
about 1 month ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
about 1 month ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
about 1 month ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
about 1 month ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs

Duan Lightfoot

Sr. AI Engineer, Akamai

Duan Lightfoot
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems

Vivek Pandit

Principal Engineer at Cadence

Vivek Pandit

Related videos

AI That Fits Your Business, Not the Other Way Around thumbnail
25:56
WWC Europe 2026 • about 1 month ago

AI That Fits Your Business, Not the Other Way Around

Anshul Jindal, Cansu Kavili Örnek

RTX AI PC: Developing local and edge AI applications thumbnail
26:06
WWC Europe 2026 • about 1 month ago

RTX AI PC: Developing local and edge AI applications

Joerg Krall

Running AI at Scale: The Secret Ingredients thumbnail
30:04
WWC Europe 2026 • about 1 month ago

Running AI at Scale: The Secret Ingredients

Boris Hecker, Max Tschochohei, Peter Kürpick, Tomislav Tipurić

The Last Mile of AI: From Prototype to Production thumbnail
28:23
WWC Europe 2026 • about 1 month ago

The Last Mile of AI: From Prototype to Production

Clemens Wasner, Holger Hammel, Martin Remmelgas, Max Jacobson, Marius Cosareanu

Open Source AI, To Foundation Models and Beyond thumbnail
31:05
WWC 2025 • about 1 year ago

Open Source AI, To Foundation Models and Beyond

Andreas Blattmann, Ankit Patel, Lucie-Aimée Kaffee, Matt White, Philipp Schmid

Your Next AI Needs 10,000 GPUs. Now What? thumbnail
29:52
WWC 2025 • 12 months ago

Your Next AI Needs 10,000 GPUs. Now What?

Anshul Jindal, Martin Piercy

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.