Verified reference stack
Developer — Local Coding — RTX 4070 Ti SUPER 14B
Ollama lists the Qwen2.5-Coder 14B package around 9.0 GB; 16 GB VRAM is a practical bounded-context reference.
Continue
Open tool profile →Ollama
Open runtime profile →Qwen2.5-Coder-14B-Instruct
Open model profile →Local model provider configuration
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 Developers
See the professional workflows and verified baselines connected to this stack.
Local AI by Hardware
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.