InsuranceLarge Language ModelsRetrieval-Augmented Generation
DACH insurance group runs an on-prem Qwen3-32B LLM for claims and underwriting staff with no data leaving its own infrastructure
A large Germany-headquartered insurance group supervised by BaFin moved an AI pilot to production by running Qwen3-32B (AWQ 4-bit, vLLM) on two NVIDIA L40S GPUs in its own server room, with no outbound internet access. An internal RAG platform serves a copilot for claims and underwriting staff plus batch summarization and classification, with SSO-bound role-based access and a per-request audit trail. Built by Valletta Software.
VSValletta Software (client: unnamed DACH insurance group)· Germany
Qwen3-32B · vLLM · NVIDIA L40S 
