Verified reference stack
Finance — Private RAG — RTX 4070
12 GB consumer reference for private RAG using a 5.2 GB Qwen3-8B package and bounded retrieval context.
Open WebUI
Open tool profile →Ollama
Open runtime profile →Qwen3-8B
Open model profile →Fully local RAG with local embeddings/model providers
Apache-2.0
Evidence
Continue the decision
Put this reference stack in context
A reference configuration is most useful when you compare it with alternatives and then apply your own hard constraints.
Private AI for Finance & Accounting
See the professional workflows and verified baselines connected to this stack.
Self-hosted RAG
Understand the architecture and privacy assumptions behind this use case.
Compare related stacks
Review this configuration beside related verified references.
Run the Stack Finder
Apply your exact profession, task, privacy requirement and hardware.
Freshness rule: Material changes set this stack to REVALIDATION_REQUIRED.