World Congress 2026 Europe • Jul 9, 2026 • Session details

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source

Viktoria Semaan

Relying on proprietary LLMs is like hiring a PhD for an intern's task. Learn how fine-tuning compact open-source models maintains top-tier accuracy while slashing production costs by 86%.

Starting at 10:14 · Watch from the beginning

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source thumbnail

Checking access…

Playback and chapters load privately for Free videos.

Matching moments

1:14 min

Evaluating AI models using an LLM as a judge

Tomislav Tipurić

Tomislav Tipurić +1 · World Congress 2026 North America

1:27 min

Key takeaways and open-source resources for model evaluation

Viktoria Semaan

Viktoria Semaan · World Congress 2026 North America

4:04 min

Evaluating model performance and accuracy using LLM judges

Viktoria Semaan

Viktoria Semaan · World Congress 2026 North America

5:58 min

Architecting inference layers and meta harnesses to manage token costs

Hari Lingamagunta

Hari Lingamagunta +3 · World Congress 2026 North America

3:01 min

Comparing open-weight, proprietary, and fine-tuned AI models

Viktoria Semaan

Viktoria Semaan · World Congress 2026 North America

4:26 min

Navigating intelligence, speed, and cost trade-offs in AI models

Viktoria Semaan

Viktoria Semaan · World Congress 2026 North America

More from World Congress 2026 Europe

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

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

Michael Kagan +1

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

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

Christian Heilmann · WeAreDevelopers

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

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

David vonThenen · NetApp

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

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

Irina Branovic · adjoe

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

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

Jeremy Murray · Stack8s

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

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

Upcoming sessions on this topic

Decision models for developers who use LLMs

Anurag Bhandari

antelligent

CTO

Stop Counting Tokens, Start Making Them Count

Vicky Israni

GitHub

Senior Solutions Engineer

The Dream Team You Didn't Know You Had - Multi-Model, Multi-Agent, One Software Lifecycle

Aditya Dua

GitHub

Senior Manager, Field Services, SAARC

How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design

Purnima Kumari

DigitalOCean

Sr. Solutions Architect II

Build a Zero-Cost AI Agent in Your Browser

Aishwarya Mathuria

Adobe

Computer Scientist
Nishant Thakur

Adobe

Senior Computer Scientist

Enterprise AI Memory at Scale

Aditya Joshi

Walmart

Senior Software Engineer

Related videos

From Model Selection to Smart Routing: How to Use the Right LLM for Every Task thumbnail

From Model Selection to Smart Routing: How to Use the Right LLM for Every Task

Viktoria Semaan · Databricks

World Congress North America · 2026

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization thumbnail

Fast, Cheap, and Accurate: Optimizing LLM Inference with vLLM and Quantization

Legare Kerrison +1

World Congress North America · 2026

Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated thumbnail

Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated

Christin Pohl · Microsoft

World Congress Europe · 2026

Unlocking the Power of AI: Accessible Language Model Tuning for All thumbnail

Unlocking the Power of AI: Accessible Language Model Tuning for All

Cedric Clyburn +1

World Congress · 2024

AI That Fits Your Business, Not the Other Way Around thumbnail

AI That Fits Your Business, Not the Other Way Around

Anshul Jindal +1

World Congress Europe · 2026

Efficient deployment and inference of GPU-accelerated LLMs thumbnail

Efficient deployment and inference of GPU-accelerated LLMs

World Congress · 2024

Related articles

BB

Benedikt Bischof

MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production

Welcome to this issue of the WeAreDevelopers Live Talk series. This article recaps an interesting talk by Bas Geerdink who gave advice on MLOps.‍About the speaker:‍Bas is a programmer, scientist, a...

about 4 years ago

MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production

BB

Benedikt Bischof

MLOps – What’s the deal behind it?

Welcome to this issue of the WeAreDevelopers Live Talk series. This article recaps an interesting talk by Nico Axtmann who introduced us to MLOpsAbout the speaker:Nico Axtmann is a seasoned machine...

about 4 years ago

MLOps – What’s the deal behind it?

IK

Igor Khokhriakov

CH

Chris Heilmann

I Gave a Video Editor More Autonomy Than a Trading Bot. On Purpose.

This is a guest post by Igor Khokhriakov. If you asked me which of two systems should get more AI autonomy, an algorithmic trading platform or a hobby video editor, the obvious answer would probabl...

about 1 month ago

Illustration of different connected systems

ME

Markus Eisele

Your AI coding tool is getting used. But is it doing anything useful?

A practical guide to reading adoption and spend data without fooling yourself. Your usage dashboard is green. Developers are active. The AI assistant is firing on all cylinders. But the sprint stil...

2 months ago

A graph showing time and money spent (which is a large bar) and actual value (which is zero).

From learning to earning

Jobs that call for the skills explored in this talk.

MLOps AI Engineer

TeamViewer Germany GmbH,

Austin, TX, United States

Expert Caching Routing Standard Sql

Machine Learning Engineer

Valladolid, Spain

Remote Twilio AutoGen Pytorch

Staff Machine Learning Engineer

Expert $160k–200k Remote AIOps Claude Twilio

Senior AI Engineer

Seattle, WA, United States

Expert $170k–231k Linux Pytorch Api Design

Machine Learning Engineer

Valencia, Spain

Remote Twilio AutoGen Pytorch

Principal Software Engineer, AI Inference Cloud

Seattle, WA, United States

$262k VLLM SGLang Pytorch