

Ollama x FriendliAI Seoul Meetup
βOllama x FriendliAI Seoul Meetup π°π·
: Building Production Agents with Open Models
βGLM, Kimi, DeepSeek, MiniMax, Nemotron λ± νλ‘ ν°μ΄ μ€ν λͺ¨λΈμ΄ λΉ λ₯΄κ² λ°μ νκ³ μμ΅λλ€. μ΄μ κ°λ°μμκ² μ€μν μ§λ¬Έμ "μ΄λ€ λͺ¨λΈμ μΈ κ²μΈκ°"λ₯Ό λμ΄, "κ·Έ λͺ¨λΈμ νλ‘λμ μ΄ μꡬνλ μλΒ·μμ μ±Β·λΉμ© ν¨μ¨λ‘ AI μμ΄μ νΈμ μ΄λ»κ² μ΄μν κ²μΈκ°"μ λλ€.
βμνλ μ€ν λͺ¨λΈμ μ ννκ³ , AI μμ΄μ νΈλ₯Ό λ§λ€κ³ , νλ‘λμ κΉμ§ κ°μ Έκ°μΈμ. Ollamaμ FriendliAIκ° μ€ν λͺ¨λΈλ‘ AI μμ΄μ νΈλ₯Ό ꡬμΆνκ³ μμ΄μ ν± μν¬λ‘λλ₯Ό νλ‘λμ κ·λͺ¨λ‘ νμ₯νλ κΈ°μ κ³Ό μ€μ μ¬λ‘λ₯Ό 곡μ ν©λλ€. λ°λͺ¨λ₯Ό λμ΄ μ€μ μλΉμ€μμ μ€ν λͺ¨λΈμ μ΄μν΄ λ³Έ λΉλλ€κ³Ό λ§λ κ²½νκ³Ό μΈμ¬μ΄νΈλ₯Ό λλμΈμ.
β(λ°ν μ£Όμ μ μ°μ¬λ μΆν μ λ°μ΄νΈ μμ μ λλ€.)
βλ€λ£° λ΄μ©
βμ€ν λͺ¨λΈλ‘ AI μμ΄μ νΈλ₯Ό μ€κ³Β·κ΅¬μΆνλ μ€μ μν¬νλ‘μ°
βλ‘컬 κ°λ° νκ²½μμ νλ‘λμ μΆλ‘ κΉμ§, μμ΄μ νΈλ₯Ό λ°°ν¬νλ λ°©λ²
βμμ΄μ ν± μν¬λ‘λμ μ§μ° μκ°Β·μ²λ¦¬λΒ·λΉμ©μ μ΅μ ννλ μ€μ μ¬λ‘
βμ€ν λͺ¨λΈ μ ν κΈ°μ€κ³Ό νλ‘λμ μ΄μμμμ νΈλ μ΄λμ€ν
βμ°Έμμ Q&A λ° λΉλ λ€νΈμνΉ
βνλ‘κ·Έλ¨
β18:00 ~ 19:00, 체ν¬μΈ λ° λ€νΈμνΉ
β19:00 ~ 19:10, νμ μΈμ¬ λ° μ€νλ (Ollama Β· FriendliAI)
β19:10 ~ 20:10, λ°ν μΈμ
βJeffrey Morgan, CEO of Ollama
βByung-Gon Chun, CEO of FriendliAI
βTBD (κ²μ€νΈ μΈμ )
β20:10 ~ 20:30, μ€ν Q&A
β20:30 ~ 21:00, λ€νΈμνΉ λ° λ§λ¬΄λ¦¬
β(μΈλΆ μΌμ μ λ³κ²½λ μ μμ΅λλ€)
βμ΄λ° λΆλ€μ κΈ°λ€λ¦½λλ€
βμ€ν λͺ¨λΈλ‘ AI μμ΄μ νΈλ LLM μ ν리μΌμ΄μ μ λ§λ€κ³ μκ±°λ λ§λ€ κ³νμΈ λΆ
βAI/ML μμ§λμ΄, λ°±μλΒ·νλ«νΌ μμ§λμ΄, μμ§λμ΄λ§ 리λ
βAI μ νμ λ§λλ ν ν¬ μ°½μ μ λ° μ΄κΈ° ν
βμ€ν λͺ¨λΈμ νλ‘λμ μ μ¬λ¦¬λ©° κ²ͺμ μνμ°©μ€λ₯Ό λλκ³ μΆμ λΆ
βOllamaλ FriendliAIλ₯Ό μ¨λ³Έ κ²½νμ νμκ° μλλλ€. μ§κΈ λ§λ€κ³ μλ κ², νκ³ μΆμ λ¬Έμ λ₯Ό ν¨κ» κ°μ Έμ μ£ΌμΈμ.
βμ°Έκ° μλ΄
βμ°Έκ°λΉ: 무λ£
βμΈμ μ νμ΄ μμ΄ λ±λ‘ ν μΉμΈλ λΆκ» μ°Έκ° νμ μλ΄λ₯Ό λ립λλ€.
βλ°ν μΈμ΄: νκ΅μ΄Β·μμ΄
βκ°λ¨ν μλ£μ λ€κ³Όκ° μ 곡λ©λλ€.
βμ₯μ
βμ½μ¬μ΄μ΄ν° μμΈμ² C, Dλ
βνΈμ€νΈ μκ°
βOllama
βOllamaμ ν¨κ»λΌλ©΄ μ΅μ μ€ν λͺ¨λΈμ μνλ νκ²½μμ μμ½κ² μ€νν μ μμ΅λλ€.
βλͺ λΆ λ§μ κ°λ°μ μμνκ³ , λ°μ΄ν°λ₯Ό μμ νκ² λ³΄νΈνλ©°, μμ μ€νμμ μ€μ νΈλν½μ μ²λ¦¬νλ μλΉμ€κΉμ§ νμ₯ν μ μμ΅λλ€. μλ°±λ§ λͺ μ κ°λ°μλ€μ΄ μ€ν λͺ¨λΈμ μμνλ κ°μ₯ μ¬μ΄ λ°©λ²μΌλ‘ Ollamaλ₯Ό μ¬μ©νκ³ μμ΅λλ€.
βFriendliAI
βFriendliAIλ μ€ν λͺ¨λΈμ νλ‘λμ μμ μλΉνλ νλ‘ ν°μ΄ AI μΆλ‘ ν΄λΌμ°λμ λλ€. Model APIs, Dedicated Endpoints, BYOG(Bring Your Own GPU)λ₯Ό ν΅ν΄ κ°λ°μμ κΈ°μ μ΄ μνλ μ€ν λͺ¨λΈμ λΉ λ₯΄κ³ μμ μ μ΄λ©° λΉμ© ν¨μ¨μ μΌλ‘ μ΄μν μ μλλ‘ μ§μν©λλ€.
βOllama x FriendliAI Seoul Meetup π°π·
: Building Production Agents with Open Models
βFrontier open models like GLM, Kimi, DeepSeek, MiniMax, and Nemotron are advancing rapidly. For developers, the question is no longer just which model to use, but how to run that model for AI agents with the speed, reliability, and cost efficiency required in production.
βChoose the open model you want. Build your AI agent. Take it to production. Join Ollama and FriendliAI to explore the technologies and real-world practices behind building AI agents with open models and scaling agentic workloads for production. Connect with builders who have taken open models beyond the demo and into real services, and share experiences and insights.
β(Talks and speakers will be announced soon.)
βWhat we'll cover
βReal-world workflows for designing and building AI agents on open models
βTaking agents from local development to production inference
βPractical lessons on optimizing latency, throughput, and cost for agentic workloads
βHow to choose an open model, and the trade-offs that show up in production
βOpen Q&A and networking with fellow builders
βProgram
β18:00 β 19:00 PM, Check-in & networking
β19:00 β 19:10 PM, Welcome & opening remarks (Ollama Β· FriendliAI)
β19:10 β 20:10 PM, Talks
βJeffrey Morgan, CEO of Ollama
βByung-Gon Chun, CEO of FriendliAI
βTBD (Guest session)
β20:10 β 20:30 PM, Open Q&A
β20:30 β 21:00 PM, Networking & wrap-up
β(Schedule subject to change)
βWho should attend
βAnyone building β or planning to build β AI agents or LLM applications on open models
βAI/ML engineers, backend and platform engineers, engineering leaders
βTechnical founders and early teams building AI products
βAnyone who wants to share the hard-won lessons of running open models in production
βNo prior experience with Ollama or FriendliAI is required. Bring what you're building and the problems you're trying to solve.
βRegistration
βAdmission: Free
βSeats are limited. Registrations are subject to approval; confirmed attendees will be notified.
βSession language: KoreanΒ· English
βLight refreshments will be provided.
βVenue
βAbout the hosts
βOllama
βOllama lets you run today's leading open models wherever you need them.
Start building in minutes, keep your data secure and grow from a first experiment to applications serving real traffic. Millions of developers have made Ollama their starting point for building with open models.
βFriendliAI
βFriendliAI is a frontier AI inference cloud serving open-weight models in production. Through Model APIs, Dedicated Endpoints, and BYOG (Bring Your Own GPU), FriendliAI helps developers and enterprises run the open models they choose with the speed, reliability, and cost efficiency production demands.