Liquid AI
Mathias Lechner
Co-founder & CTO
Efficient models for local intelligence. A conversation about the architectures and practical constraints shaping the next generation of on-device agents.
NOVEMBER, WEDNESDAY 18, 2026 · SAN FRANCISCO
On-Device
Agents.
The next frontier of AI is closer than you think.
A technical mini-conference exploring the models, silicon, and systems that put useful agents on the devices we already own.
BROUGHT TO YOU BY
6:00–9:00 PM PST
San Francisco, Liquid AI HQ
ONE EVENING. THE COMPLETE STACK.FROM ARCHITECTURE TO REAL-WORLD PERFORMANCE
01
Model
Efficient architectures. Open weights. Models designed for local, agentic workloads.
02
Compute
NPUs and Apple silicon. Quantization, memory, and power. Making inference work on-device.
03
Benchmark
Measure the deployed system. Quality, latency, and efficiency under real constraints.
THE PEOPLE BUILDING IT
The Speakers
Researchers, engineers, and founders.
In the same room. In conversation.
ZETIC
Yeon Kim
Founder & Technical Lead
Hardware-aware optimization and deployment across devices. A conversation about getting models to run fast on every chip.
MacPaw
Sergii Kryvoblotskyi
Director of AI & Research
Turning on-device intelligence into useful consumer applications.
Qualcomm
Zack Li
Engineering Lead, Gen AI Inference · Co-founder & CTO of Nexa AI
NPUs, hardware acceleration, and the realities of deploying AI on devices. A conversation about running fast, fully on-device inference on the Qualcomm NPU.
Cactus Compute
Henry Ndubauku
Local inference and practical agent workflows on everyday hardware.
Artificial Analysis
Comparing local models on quality, speed, and efficiency.
Speaker TBD
RunAnywhere
Developer tools and inference runtimes for shipping local AI.
Speaker TBD
Together AI
Where local agents meet cloud inference, and how to split the workload.
Speaker TBDAlso exploring a technical session with Nexa AI on edge and NPU inference. Speaker to be confirmed.
7:30–9:10 PM · ON STAGE
Tech Talks
Four short technical talks.
15 minutes on stage, 10 minutes of questions.
- Talk 017:30–7:55PM
Talk TBD
Speaker to be announced7:30 Talk · 15 min7:45 Q&A · 10 min - Talk 027:55–8:20PM
Talk TBD
Speaker to be announced7:55 Talk · 15 min8:10 Q&A · 10 min - Talk 038:20–8:45PM
Talk TBD
Speaker to be announced8:20 Talk · 15 min8:35 Q&A · 10 min - Talk 048:45–9:10PM
Talk TBD
Speaker to be announced8:45 Talk · 15 min9:00 Q&A · 10 min
Talks are selected from the speaker lineup above. Want one of these slots? Propose a talk.
THE COMPANIES IN THE ROOM
Sponsors
The companies making the evening possible.
Presenting sponsor
Liquid AI builds efficient foundation models designed to run where the data is: on phones, laptops, vehicles, and edge devices. Our host and presenting sponsor for the evening.
Platinum
Put your brand at the center of on-device AI.
We’re curating sponsors building the on-device agent stack, from models and inference runtimes to hardware, benchmarks, and the apps that ship it.
LIQUID AI ECOSYSTEM
Partners
Liquid AI’s partners across the AI stack.
THE EVENING
Bring your
hard questions.
Technical presentations meet Socratic dialogue. Come to compare approaches, challenge assumptions, and meet the people working through the same problems.
Wednesday, November 18All times Pacific · Program subject to change
- 6:00PM
Doors open
Food, drinks, and conversations with the people building the stack.
- 6:30PM
Meet the room
Host introductions and a quick round of introductions from attendees.
- 7:00PM
Socratic dialogues
A focused 30-minute discussion on on-device agents: what works, what breaks, and what comes next.
- 7:30PM
Technical talks + Q&A
Focused 15-minute presentations, each followed by 10 minutes of questions. Talks to be announced.
- 7:30Talk 01 · TBDQ&A 7:45
- 7:55Talk 02 · TBDQ&A 8:10
- 8:20Talk 03 · TBDQ&A 8:35
- 8:45Talk 04 · TBDQ&A 9:00
- 9:10PM
Keep the conversation going
Optional networking at a nearby bar.
REGISTRATION
Invite only
Attendance is by invitation. Ask to join on Luma — every request is reviewed to keep the room technical.
GET IN THE ROOM
Build what
comes next.
For AI researchers and engineers working on small local models and on-device agents. Participation is curated to keep the conversation technical and high signal.
Hosted by Federico Ulfo, Viviana Marquez, …