JAIS Series
World’s most advanced
Arabic LLM
Arabic LLM
K2 Series
World's most transparent
high-performance LLM
high-performance LLM
National Sovereign /Heritage
Models
NANDA - World’s most
advanced Hindi LLM
advanced Hindi LLM
Chatbot Arena
A global platform that uses LLM as judge to evaluate other LLMs
Vicuna
High-performance LLM within a cost
of $300 to build
of $300 to build
FM for Bio
GET - A state-of-the art foundation model for gene activity in cells
World Model
The next-generation FM for embodied reasoning and physical-world simulation beyond
LLM
LLM360
A global platform for
“360-open-source” LLMs
“360-open-source” LLMs
Who We Are
The Institute of Foundation Models is dedicated to pioneering academic research at the forefront of Generative AI, driven by real-world societal needs. As a central hub for fundamental research, we are channeling our expertise into developing powerful foundation models—such as GPTs—for linguistic, visual, and biological data. These models have the potential to revolutionize industries like healthcare, climate change, and sustainability while simultaneously advancing AI innovation.
Message from the President
At IFM, we are committed to advancing Generative AI in ways that truly make a difference. Innovation carries responsibility, and our goal is to drive meaningful progress with social impact.
Our research is not just about what technology can achieve, but how it can be used ethically to address global challenges, transform industries, and set new standards for responsible AI.
The future is shaped by those who innovate with purpose—let’s build it together.
Our Models
Our portfolio encompasses large language models, specialized foundation models, and collaborative platforms like LLM360 that drive AI innovation.
Keep
Scrolling to See
More Models!
Large
Language
Models
JAIS Series
Jais, an open-source Arabic large language model, surpasses existing models
in quality and competes strongly with English models despite limited English
data, serving over 400 million Arabic-speaking individuals worldwide.
K2 Series
K2 sets new standards in transparency and performance for open-source
artificial intelligence (AI) by providing a blueprint for documenting and
studying the full lifecycle of LLMs, including all reproduction details.
SHERKALA
SHERKALA, is an 8-billion-parameter model that is adaptively trained on 45
billion words, primarily focusing on Kazakh while also including English,
Russian, and Turkish. SHERKALA sets a new benchmark for Kazakh LLMs by
excelling in Kazakh understanding and generative evaluations.
NANDA
Nanda is a 10-billion parameter model, which demonstrates better knowledge
and reasoning capabilities in Hindi than any existing open Hindi and
multilingual models of similar size by a sizable margin.
Vicuna
Vicuna is a lightweight, open-source LLM chatbot fine-tuned with
user-shared
conversations from ShareGPT, surpasses 90% quality of OpenAI
ChatGPT and Google Bard, outperforming models like LLaMA and Stanford Alpaca
in over 90% of cases, all achieved at a training cost of approximately $300.
Keep
Scrolling to See
More Models!
Specialised Models
FM For Bio - GET
GET is a foundation model for transcriptional regulation that
accurately
predicts gene expression in diverse human cell types, adapts to
different conditions and sequencing platforms, and identifies regulatory
elements and interactions, making it a valuable tool for gene regulation
analysis.
World Model
The next-generation FM for embodied reasoning and physical-world simulation
beyond LLM
Keep
Scrolling to See
More Models!
Collaborative Platforms
LLM360
LLM360 is a groundbreaking open-source framework aimed at enhancing
transparency and collaboration in AI research.
It offers detailed insights by providing full access to training processes,
including checkpoints, datasets and source code for models like Amber and
CrystalCoder. LLM360 aims to democratize LLMs by offering a framework for
open-source LLMs to foster transparency, trust, and collaborative research.
Latest News
April 29, 2025
Launch Event of MBZUAI’s Institute of Foundation Models (IFM)
MBZUAI is proud to unveil the Institute of Foundation Models (IFM) — a bold, global initiative uniting top AI talent across Abu Dhabi, Silicon Valley, and Paris. We invite researchers, technologists, and innovators to join us in Silicon Valley as we celebrate this milestone.
January 21, 2025
Making MBZUAI the “Stanford of the Middle East”
MBZUAI President and University Professor Eric Xing announces ambitions for 2025 and beyond in his New Year, New Journey address.
October 30, 2024
MBZUAI releases Nanda giving over half billion Hindi
speakers access to world’s best open-source Hindi LLM
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) – the world's first graduate-level artificial intelligence (AI) university dedicated to research – has released Nanda, the world’s most advanced open-source Hindi large language model (LLM).
May 30, 2024
Large language model K2-65B launches globally, setting
a new standard for sustainable performance
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), in collaboration with Petuum and LLM360, announces the launch of K2-65B, a ground-breaking open-source 65-billion parameter large language model (LLM). K2 sets new standards in transparency and performance for open-source artificial intelligence (AI) by providing a blueprint for documenting and studying the full lifecycle of LLMs, including all reproduction details.
Upcoming Events
AI for a Sustainable Future
Symposium
Date:
January 06, 2025
Time:
3:00 PM - 6:00 PM
Description: Part of a series of symposiums exploring the role of AI in promoting sustainability across various sectors
Note: Focuses on Generative AI advancements, applications, and ethics—ideal for researchers, students, and professionals.
AI for Social Sciences and Humanities
Symposium
Date:
January 06, 2025
Time:
3:00 PM - 6:00 PM
Description: Part of a series of symposiums exploring the role of AI in promoting sustainability across various sectors
Note: Focuses on Generative AI advancements, applications, and ethics—ideal for researchers, students, and professionals.
MBZUAI Workshop 2025: Foundations and
Advances in Generative AI
Date:
January 06, 2025
Time:
3:00 PM - 6:00 PM
Description: Part of a series of symposiums exploring the role of AI in promoting sustainability across various sectors
Note: Focuses on Generative AI advancements, applications, and ethics—ideal for researchers, students, and professionals.
Work with Us
Drive the future of foundation models. We're looking for brilliant minds to help us push the boundaries of AI research and applications. Find your place on our team and apply now.
World-leading Research, Global Footprints
Silicon Valley
MBZIFM drives AI innovation in scalable foundation models, ethical AI, and tech-driven sustainability, leveraging Silicon Valley’s ecosystem of research and entrepreneurship.
Paris
MBZIFM advances AI for multilingual modeling, sustainability, and smart infrastructure, leveraging Paris’s role as a global innovation hub.
Abu Dhabi
MBZIFM advances AI for Arabic language processing, sustainability, and smart cities, leveraging Abu Dhabi’s role as a global tech hub.
Contact Information
We’re here to collaborate and connect. For inquiries or partnerships, reach out to us: