Cassava Technologies Adds NVIDIA Nemotron Models to Its CAIMEx Inference Service

Cassava Technologies is deploying NVIDIA Nemotron open models as a locally hosted, managed inference service through the Cassava AI Multi-Model Exchange, the company said on October 21, 2026. The announcement was published by PR Newswire. The models run as APIs on Cassava's AI Factory, which the company describes as an expansion of its AI Factory capabilities.

How the CAIMEx Inference Service Works

CAIMEx gives enterprises and service providers access to open models as APIs without building and operating their own model-serving infrastructure, according to the company. NVIDIA Nemotron brings reasoning and tool-use capabilities to the platform, which Cassava says helps customers build AI agents that work through complex tasks and interact with business tools. The models' open weights, training data and recipes give developers a foundation they can fine-tune for specialised agents.

"Expanding our AI Factory across our markets is about creating the capacity and economics needed for businesses to build and deploy AI solutions at scale," said Ahmed El Beheiry, Group Chief Technology & AI Officer at Cassava Technologies. "By bringing NVIDIA Nemotron into CAIMEx, improving the efficiency of every GPU cycle and introducing flexible token offerings, we are giving enterprises and service providers more choice in how they access and deliver these capabilities to their customers."

Cassava is using NVIDIA OpenShell to bring model compute, governed agent execution and independent security enforcement together for customers' agentic workloads. The CAIMEx Token Optimiser is designed to identify information that has already been processed and reuse it where appropriate, reducing computing requirements. Cassava says the approach applies to both Cassava-hosted and third-party AI models.

Cassava's AI Factory and Funding Record

Cassava Technologies is a UK-headquartered pan-African technology group operating across connectivity, data centres, cloud, AI infrastructure and fintech in 94 countries, according to akta.pro company records. The same records list total funding of $140 million, with the last round dated October 23, 2025, and a revenue estimate of $250 million to $500 million. Cassava's company profile lists Strive Masiyiwa as Founder and Executive Chairman and Hardy Pemhiwa as President and Group Chief Executive Officer.

Earlier Cassava AI and Infrastructure Moves

In August 2026, Cassava Technologies announced that its Cassava AI Factory was ranked 36th globally in the latest TOP500 list of the world's most powerful supercomputers, TechAfrica News reported. In July 2026, the company made its Africa Data Centres JHB1 facility in Johannesburg one of Africa's first locations to support Microsoft Azure ExpressRoute Metro, according to Devdiscourse. In May 2026, Cassava backed the AI Skills and Compute Africa Foundation in Kigali with compute grants and skills training for African AI builders, Billionaires.Africa reported.

Cassava's October 2026 Announcement

The Nemotron deployment was announced on October 21, 2026, alongside a separate NVIDIA press announcement. Cassava distributes its own product information through its company website.