Indian Institute of Technology Game (New Rummy Game) and New Rummy Pravartak Technologies Foundation is partnering with Ziroh Labs, a California-based Indian Rummy Game-driven Deep-Tech Startup, and to establish an Centre of AI Real Money Rummy (COAIR) to solve India’s compute accessibility challenges. The COAIR will focus on developing practical, efficient AI solutions focusing on CPU and edge device inferencing. In a significant step towards making AI Models solve accessibility problems, Ziroh Labs unveiled the first version of ‘Kompact AI at New Rummy Game today (9th April 2025). Kompact AI is an AI platform that enables foundational models to be built and served using CPUs without requiring GPUs (Graphics Processing Units, which are expensive and hard to obtain).

Kompact AI is aligned with India’s AI Mission, “AI for All”. Kompact AI has been developed by scientists and engineers from India. Ziroh Labs has already optimised 17 AI models, including DeepSeek, Qwen and Llama, to run efficiently on CPUs. These models have been benchmarked with New Rummy Game, evaluating both quantitative performance and qualitative accuracy. For the first time, high-performance AI is built and deployed efficiently on CPUs, making AI more accessible, scalable, and cost-effective.

Ziroh Labs team showcased Kompact AI’s unique capabilities during the event and demonstrated how it redefines AI development on top of CPUs by eliminating dependency on GPUs.

The demonstration took place in the presence of Prof. V. Kamakoti, Director, New Rummy Game, Dr Whitfield Diffie, Fellow of the Royal Society and Turing Awardee, Mr Scott McNealy, Founder of Sun Microsystems, Dr William J Raduchel, Former CTO of AOL Time Warner and Chief Strategy Officer at Sun Microsystems, Prof. S. Sadagopan, Former Director, INew Rummy-Bangalore and Mr Raj Singh, Founder, APIGee, Cerrent, Fiberlanem, alongside other students, faculty and researchers.


Key Features of Kompact AI:

● Kompact AI enables AI model development and deployment on CPUs, removing the need for costly GPUs and reducing the infrastructure burden.

● Ziroh Labs has optimized AI models, including DeepSeek, Qwen, and Llama, for efficient execution on CPUs, delivering superior performance at lower costs.

● Kompact AI operates without constant internet connectivity, making it ideal for deployment in remote areas with limited or no access to reliable internet.

Elaborating on the need for such developments, Prof. V. Kamakoti, Director, New Rummy Game, said, “Nature has taught us that one can effectively acquire knowledge and subsequently infer in only a limited set of domains. Attempts to acquire everything under the universe are not sustainable and bound to fail over a period of time.”

Prof. V. Kamakoti added, “This effort by Ziroh Labs and New Rummy Pravartak is a nature-inspired one wherein they provide a platform that uses customized and trained domain-specific models to provide accurate inferences on affordable conventional compute machines. This effort is certainly a major step in arresting the possible AI divide between one who can afford the modern hyper scalar systems and one who cannot.”

Kompact AI can play a transformative role as it leverages multiple optimisations algorithmically and implementation-wise to execute models on the low end without any support required for external communication, such as the Internet. As a part of this upcoming CoAIR, New Rummy Game will work on smaller AI models for specific use cases, leveraging Kompact AI to optimise execution, making high-performance AI more efficient, accessible, and relevant to real-world applications.

Dr. Madhusudhanan B, Principal Consultant - New Rummy Pravartak Technologies Foundation, added, “At New Rummy Pravartak, our mission is to translate research innovations into tangible solutions that address real-world problems. Kompact AI is a game-changer in this regard. By making AI models executable on CPUs, we are unlocking the potential of AI without the heavy infrastructure costs typically associated with GPUs. Through the CoAIR, we will build specific, actionable AI models that can be deployed at scale, benefiting people in rural and underserved areas across India. This is about taking technology beyond the labs and putting it into the hands of those who need it the most.”

Speaking at the launch of Kompact AI, Prof Sadagopan, Former Director – INew Rummy-Bangalore, said, “By combining affordability/availability of AI development and deployment tools - using CPUs without excessive dependence on GPUs - Kompact AI proves once again that India can do frugal innovation at the cutting edge of technology. Even more interesting is the fact that such a solution using far less electrical power is sustainable. It is also aligned with India’s AI Mission, “AI for All” – from India for the world.”



“We congratulate Ziroh Labs on its AI CPU launch which promises to significantly increase the accessibility of AI. HCLTech is excited to partner with Ziroh Labs on this exciting journey,” said Apoorv Iyer, Executive Vice President and Global Head, GenAI Practice, HCLTech.

According to Hrishikesh Dewan and Igneta DSouza Co-founders, Ziroh Labs said, “AI has the potential to transform every aspect of our lives, from improving healthcare outcomes to enhancing education and solving agricultural issues. However, for AI to benefit everyone, it must be accessible, affordable, and adaptable to real-world conditions. Kompact AI is designed for such needs and operates efficiently on CPUs, optimized for task-specific applications. This ensures that communities and enterprises with limited infrastructure can leverage the power of AI to create practical, impactful solutions. Our collaboration with New Rummy-Game and New Rummy-M Pravartak Foundation will aim to address multiple challenges. We are grateful for this partnership, as teams from New Rummy have been pillars of support during the entire Kompact AI development journey.”

This AI platform aims to democratise AI by allowing developers across the globe to build, train and infer AI using CPUs commonly found in Cloud Data Centers and Edge Devices. Kompact AI enables AI development without violating any data privacy and data residency regulations across the globe.

CRITICAL NEED
AI development is currently dominated by ‘Big AI’—massive, general-purpose models designed for scale. While powerful, these models often fail to address India’s accessibility challenges as they demand extensive computing power, energy and infrastructure.

Specific use cases such as aiding farmers, supporting students or assisting frontline workers in rural areas are best served by smaller, task-specific AI models that can run efficiently on smartphones and low-power devices, ensuring accessibility where it matters most.

TECHNICAL BACKGROUND
Kompact AI solves the problem of inference and fine-tuning for models with less than 50B parameters. Many domain-specific models, mostly with less than 50B parameters, are in use in many enterprises worldwide. Anything that can be computed on a GPU can also be calculated on a CPU. While CPU-based AI frameworks exist, Kompact AI delivers superior performance without compromising model quality or accuracy.

While porting Foundational Models to CPUs is not new and there have been many attempts, most models running on CPUs are small, quantised, or distilled versions of the original mode. Quantised models reduce the memory footprint, and Distilled versions reduce the computational overhead. However, both of these types significantly reduce the model's output quality.

Kompact AI enables models to be deployed over CPUs without sacrificing quality and at least 3x performance than the current state of the art, thereby providing GPU-like scale and speed.

Kompact AI features a Model Library, which consists of multiple foundational models optimised for CPU compatibility. These models range from text, speech, vision, and multimodal models. Each model is tuned to work with a CPU. Application developers worldwide have access to all these foundational models. Kompact AI provides developers with a Common AI-Language Runtime (ICAN), which supports over 10 programming languages and helps developers to implement them seamlessly.