distil labs builds specialized models for AI agents on Nebius AI Cloud using synthetic data. Its platform prepares evaluation sets and synthetic training data from production traces, trains and scores small models, and offers deployment behind an OpenAI-compatible endpoint.
For Knowunity’s English quiz generator, distil labs reports post-training NVIDIA Nemotron 3.5 Lightning using NVIDIA NeMo RL on Nebius H100 GPUs. Supervised fine-tuning took about 20 GPU-hours, followed by about 48 GPU-hours of reinforcement learning. The resulting model serves a large portion of Knowunity’s English quiz traffic.
In an evaluation of 114 production requests judged by Claude Opus 4.8, 65% of its quizzes passed all four review criteria, compared with 39% for the incumbent.
Knowunity's quiz generator now runs on a post-trained NVIDIA Nemotron with 3B active parameters
Published 20 Oct 2026 · distil labs · Web page
distil labs reports supervised fine-tuning and reinforcement learning of Knowunity’s quiz model on Nebius H100 GPUs using NVIDIA NeMo RL. The case study reports production rollout and an evaluation of 114 English quiz requests in which 65% passed all four review criteria, compared with 39% for the incumbent.
Knowunity's quiz generator now runs on a post-trained NVIDIA Nemotron with 3B active parametersPublished 20 Oct 2026 · distil labs · Web pagedistil labs reports supervised fine-tuning and reinforcement learning of Knowunity’s quiz model on Nebius H100 GPUs using NVIDIA NeMo RL. The case study reports production rollout and an evaluation of 114 English quiz requests in which 65% passed all four review criteria, compared with 39% for the incumbent.
Nebius Q3 2026 letter to shareholders
Published 12 Nov 2026 · Nebius Group · PDF
Nebius states that Distil Labs is building specialized models for AI agents on Nebius AI Cloud using synthetic data.
Nebius Q3 2026 letter to shareholdersPublished 12 Nov 2026 · Nebius Group · PDFNebius states that Distil Labs is building specialized models for AI agents on Nebius AI Cloud using synthetic data.
distil labs is a Berlin-based software company operated by Distil Labs GmbH. Its platform helps developers and AI product teams build task-specific small language models for recurring agent tasks. Users provide a task description, examples, or production traces; the platform prepares evaluation and training data, post-trains and scores a model, then supports deployment through an inference endpoint or in a customer’s own environment. The company also offers a CLI and API for running the workflow.
Distil Labs launches an inference endpoint to capture production traffic
Distil Labs introduced an inference endpoint that captures requests and responses while a customer’s existing LLM continues answering. The captured traffic can then serve as starting data for training a small model.
A Berlin-based post-training platform that turns production traces into task-specific small language models. · Infrastructure
How they use Nebius AI Cloud
distil labs builds specialized models for AI agents on Nebius AI Cloud using synthetic data. Its platform prepares evaluation sets and synthetic training data from production traces, trains and scores small models, and offers deployment behind an OpenAI-compatible endpoint.
For Knowunity’s English quiz generator, distil labs reports post-training NVIDIA Nemotron 3.5 Lightning using NVIDIA NeMo RL on Nebius H100 GPUs. Supervised fine-tuning took about 20 GPU-hours, followed by about 48 GPU-hours of reinforcement learning. The resulting model serves a large portion of Knowunity’s English quiz traffic.
In an evaluation of 114 production requests judged by Claude Opus 4.8, 65% of its quizzes passed all four review criteria, compared with 39% for the incumbent.
Knowunity's quiz generator now runs on a post-trained NVIDIA Nemotron with 3B active parameters
Published 20 Oct 2026 · distil labs · Web page
distil labs reports supervised fine-tuning and reinforcement learning of Knowunity’s quiz model on Nebius H100 GPUs using NVIDIA NeMo RL. The case study reports production rollout and an evaluation of 114 English quiz requests in which 65% passed all four review criteria, compared with 39% for the incumbent.
Knowunity's quiz generator now runs on a post-trained NVIDIA Nemotron with 3B active parametersPublished 20 Oct 2026 · distil labs · Web pagedistil labs reports supervised fine-tuning and reinforcement learning of Knowunity’s quiz model on Nebius H100 GPUs using NVIDIA NeMo RL. The case study reports production rollout and an evaluation of 114 English quiz requests in which 65% passed all four review criteria, compared with 39% for the incumbent.
Nebius Q3 2026 letter to shareholders
Published 12 Nov 2026 · Nebius Group · PDF
Nebius states that Distil Labs is building specialized models for AI agents on Nebius AI Cloud using synthetic data.
Nebius Q3 2026 letter to shareholdersPublished 12 Nov 2026 · Nebius Group · PDFNebius states that Distil Labs is building specialized models for AI agents on Nebius AI Cloud using synthetic data.
distil labs is a Berlin-based software company operated by Distil Labs GmbH. Its platform helps developers and AI product teams build task-specific small language models for recurring agent tasks. Users provide a task description, examples, or production traces; the platform prepares evaluation and training data, post-trains and scores a model, then supports deployment through an inference endpoint or in a customer’s own environment. The company also offers a CLI and API for running the workflow.
Distil Labs launches an inference endpoint to capture production traffic
Distil Labs introduced an inference endpoint that captures requests and responses while a customer’s existing LLM continues answering. The captured traffic can then serve as starting data for training a small model.