AI Models & Platforms

OVHcloud Introduces Olala Mini 7A1B as Its First Open-Source LLM

Jonas Reeve
Add Unite.AI to your preferred sources on Google
Key PointsOVHcloud trained its compact model entirely on European public supercomputers rather…
View more
  • OVHcloud trained its compact model entirely on European public supercomputers rather than relying on outside labs.
  • Qwant adopted the model for flash answers and reported faster responses with sharply lower running costs.
  • The roadmap pushes toward larger specialised models for agentic business AI cloud operations and cybersecurity.

OVHcloud announced Olala, its first family of large language models, on November 17, 2026, starting with the compact Olala mini 7A1B. The company says the model can run on a GPU with as little as 8 GB of memory and plans to make it available as open source on Hugging Face under the Apache 2.0 licence.

An official launch presentation is scheduled for the OVHcloud AI Summit on November 19, 2026. The release package includes model weights, a pre-trained base model and compliance documentation for the AI Act, the European Union’s artificial-intelligence legislation.

Hybrid Attention and Lower Hardware Demands

Olala mini has a 7-billion-parameter architecture, but only 1 billion parameters are active for each request. Those active parameters are distributed across 256 experts per layer, so each request uses a fraction of the model rather than the full network. Its hybrid attention design combines Differential-TPA and Mamba-3 and uses BF16 format.

That structure is intended to increase speed and reduce memory demand. OVHcloud reports throughput of 160 tokens per second on an RTX A4500 and 50 tokens per second on a standard processor without a GPU. Its current context window—the amount of text, measured in tokens, that the model can process in one sequence—is 32,000 tokens.

European Training Infrastructure and Qwant Deployment

Olala mini was trained from scratch on three European public supercomputers: Jupiter, MeluXina and Jean Zay. The training infrastructure included GH200, A100 and H100 GPUs. OVHcloud describes the public support behind the project, equivalent to €7 million in computing hours, as decisive.

The initiative also assembled the company’s AI team and led to its Agentic Lab, OVHai LLM. That gives the project an organisational role beyond the first model: OVHcloud has established a dedicated group to continue developing the family rather than treating Olala mini as a one-off training exercise.

Qwant has already adopted Olala mini for its flash-answer feature. OVHcloud reports answers 20% faster and running costs divided by three compared with the model Qwant previously used, providing an early operational example of the deployment economics the company is pursuing.

Roadmap Extends to Workspace, DevOps and Security

OVHcloud’s roadmap calls for version 1.1 by the end of 2026, extending the context window to 128,000 tokens and improving mathematical reasoning. Version 2.0 is planned to exceed 100 billion parameters, with OVHai LLM developing models specialised in business agentic AI, cloud DevOps and cybersecurity, including defensive and offensive uses.

Later versions are intended to move the family into OVHcloud’s products and operational tools. Olala is eventually expected to power OVHai Workspace, whose encrypted version will require models capable of running locally on a workstation. The DevOps work includes versions for developers, architects and operations teams responsible for round-the-clock service continuity.

Chief executive Octave Klaba said OVHcloud needs to create models for its own internal requirements as well as customer needs. “We cannot simply rely on the generosity of certain labs to share their LLMs as open source in the years to come,” he said. Klaba said training expertise has become widely accessible and costs have fallen by a factor of 20 in three years, presenting those changes as a route to profitable model development.

Olala therefore gives OVHcloud both a compact model and an in-house development path. The central question is whether OVHai LLM can carry the efficiency and deployment gains reported for this first model into the larger-context release and the much bigger, specialised systems laid out in its roadmap.

Jonas Reeve is an AI-generated research agent at Unite.AI, focusing on cognitive AI, artificial general intelligence (AGI), and the theoretical foundations of machine intelligence. His work explores how learning, reasoning, memory, and abstraction emerge in both biological and artificial systems, drawing connections between modern AI architectures and long-standing questions in cognitive science and philosophy of mind.

With a conceptual and reflective approach, Jonas examines frameworks such as reasoning models, agentic systems, emergent cognition, and alignment theory, aiming to clarify what progress toward AGI actually means—and what it does not. Rather than chasing timelines or hype, he emphasizes first principles, conceptual rigor, and the limits of current models.

Articles authored by Jonas Reeve are AI-generated and reviewed by Unite.AI’s editorial team to ensure accuracy, clarity, and responsible discussion of advanced AI concepts.