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

Fine-Tuning Small Language Models for Agentic AI

Björn Buchhold

Massive frontier models are bottlenecking your agentic AI workflows. Discover how fine-tuning specialized small language models on a single GPU slashes inference costs without sacrificing domain-specific performance.

Pause
Mute Enter Fullscreen
#1 about 7 min

The case for fine-tuning small models in agentic AI

Specialized small language models can replace large models for specific agentic subtasks to reduce costs and latency.

#2 about 4 min

Benchmarking text-to-SQL tasks with custom datasets

Custom training and evaluation datasets for manufacturing and hospital domains help benchmark agentic performance effectively.

#3 about 2 min

Comparing Claude Sonnet and Qwen for text-to-SQL generation

Claude Sonnet serves as the baseline large language model against candidate small model Qwen 4B.

#4 about 4 min

Methods for supervised fine-tuning and reinforcement learning

Data distillation enables supervised fine-tuning while GRPO offers reinforcement learning with verifiable rewards.

#5 about 3 min

Analyzing performance results on the manufacturing dataset

Supervised fine-tuning approaches the text-to-SQL quality of baseline large models on in-domain tasks.

#6 about 2 min

Implementing simple supervised fine-tuning with the Unsloth library

Specific training prompts and the Unsloth library streamline the process of fine-tuning quantized models.

#7 about 2 min

Evaluating model generalization on out-of-distribution schemas

Fine-tuned models excel narrowly in their trained domain but struggle to generalize to new schemas without reasoning skills.

#8 about 4 min

Designing effective reward functions for reinforcement learning algorithms

Evaluating SQL queries introduces nuance that makes building reliable reward functions for GRPO mathematically complex.

#9 about 3 min

Benchmark limitations and final recommendations for fine-tuning models

Despite evaluation limits, supervised fine-tuning offers clear return on investment for highly specialized sub-agent tasks.

#10 about 1 min

Answering questions on hardware requirements and GPU limitations

The Unsloth library enables local small language model training on a single A10 cloud GPU.

Matching moments

5:01 min

Leveraging large language models for code optimization and development

Stephan Gillich Stephan Gillich +3 · World Congress 2024

3:35 min

Moving beyond generalist models with local fine tuning

Cedric Clyburn Cedric Clyburn +1 · World Congress 2024

2:37 min

Understanding core parameters and mechanics of large language models

Julián Duque Julián Duque · World Congress 2025

1:59 min

Identifying when narrow tasks require custom model fine-tuning

Viktoria Semaan Viktoria Semaan · World Congress 2026 Europe

1:21 min

Cost considerations of fine-tuning large language models

Kevin Klues Kevin Klues

1:45 min

Introduction to serving large language models locally

Patrick Koss Patrick Koss · World Congress 2025

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
about 2 months 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 2 months 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 2 months 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 2 months 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 2 months 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 2 months 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

September 24, 2026 · 17:30–18:00

Stage 6

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

September 24, 2026 · 16:10–16:40

Stage 9

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

Legare Kerrison, Cedric Clyburn

Legare Kerrison
Cedric Clyburn
Open session

World Congress 2026 North America

September 25, 2026 · 11:40–12:10

Stage 9

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

September 23, 2026 · 10:45–12:45

Stage 10

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

September 24, 2026 · 14:10–14:40

Stage 5

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

September 24, 2026 · 13:30–14:00

Stage 9

Understanding LLM Architectures: Inside the Design of Modern Models

Jofia Jose Prakash

Director - AI & Governance at Humanity + AI, Inc

Jofia Jose Prakash

Related videos

Unlocking the Power of AI: Accessible Language Model Tuning for All thumbnail
31:50
World Congress 2024 • about 2 years ago

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

Cedric Clyburn, @technicallylegare

Cutting LLM Costs Without Cutting Quality: How to Beat Proprietary LLMs with Fine-Tuned Open Source thumbnail
29:50
World Congress 2026 Europe • about 2 months ago

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

Viktoria Semaan

How AI Models Get Smarter thumbnail
35:16
World Congress 2025 • about 1 year ago

How AI Models Get Smarter

Ankit Patel

Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated thumbnail
30:40
World Congress 2026 Europe • about 2 months ago

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

Christin Pohl

Inside the Mind of an LLM thumbnail
27:11
World Congress 2025 • about 1 year ago

Inside the Mind of an LLM

Emanuele Fabbiani

Rules, Heuristics, or LLMs? Lessons from Solving the Same Problem Twice thumbnail
22:16
World Congress 2026 Europe • about 2 months ago

Rules, Heuristics, or LLMs? Lessons from Solving the Same Problem Twice

Artur Naumenko

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.