New availability as part of NVIDIA AI Enterprise expands access to high-performance, secure LLMs for private deployment
TEL AVIV, ISRAEL / ACCESS Newswire / June 12, 2025 / AI21 today announced that its Jamba 1.6 model is now available as a downloadable NVIDIA NIM microservice, supported by the NVIDIA AI Enterprise software platform. The release unlocks faster, easier access for enterprise developers looking to deploy high-performing, secure LLMs (large language models) across public and private infrastructure.
Jamba is AI21’s family of LLMs designed for enterprise use, optimized for long-context processing, low latency, and efficient hardware utilization. With this new NIM availability, enterprise teams can now deploy Jamba 1.6 in under five minutes via standardized APIs – whether in cloud environments such as AWS, Azure, or GCP, or on-premises with NVIDIA-accelerated infrastructure.
The release is made possible by NIM microservices, which streamline the integration of a broad range of LLMs into enterprise workflows. This is a major milestone in expanding AI21’s footprint within the NVIDIA developer ecosystem and providing a faster path to AI deployment for global enterprises.
“Jamba 1.6 is a benchmark leader for secure, private deployment, especially for enterprises that can’t compromise on performance, reliability, or data privacy,” said Ori Goshen, AI21’s CEO and Co-Founder. “We’ve seen strong demand for private deployments in financial services, legal, and healthcare, where our customers have struggled to find a model that meets both their security needs and performance expectations. Jamba is that model.”
The Jamba 1.6 NIM provides:
Plug-and-play deployment through NVIDIA AI Enterprise l with NIM microservices
Private and hybrid-cloud flexibility, supporting on-prem, multi-cloud, and regulated environments
Best-in-class latency and context window, ideal for AI agents and RAG (retrieval-augmented generation) use cases
Enterprise-grade security, delivered through NVIDIA’s continuously managed AI Enterprise stack
Jamba is already in use by leading enterprise customers powering high-stakes AI applications across legal document processing, internal knowledge agents, and real-time customer service tools. The new NIM support makes it easier than ever to adopt Jamba in production environments that require trust, transparency, and speed.
AI21’s Jamba 1.6 NIM can be deployed using the universal LLM NIM microservice. Get started today at build.nvidia.com.
About AI21
AI21 is a pioneer in Foundation Models and AI Systems designed for enterprises. AI21’s mission is to create trustworthy artificial intelligence that powers humanity towards superproductivity. Founded in 2017 by AI visionaries Prof. Amnon Shashua, Prof. Yoav Shoham, and Ori Goshen, AI21 has secured $336 million in funding from industry leaders, including NVIDIA, Google, and Intel, reinforcing its commitment to advancing AI innovation.
SOURCE: AI21
