Verified reference stack

Developer — Local Coding — RTX 4060 8 GB

Ollama package is 4.7 GB Q4_K_M. Context size must remain compatible with remaining VRAM; Stackelier must expose context as part of the hardware profile.

Application

Continue

Runtime

Ollama

Model

Qwen2.5-Coder-7B-Instruct Q4_K_M

Hardware

RTX 4060 8 GB / 32 GB RAM

GOOD_WITH_BOUNDED_CONTEXT

Privacy

Fully local configuration

License / terms

Apache-2.0

Evidence

https://docs.continue.dev/customize/model-providers/top-level/ollama
https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
https://ollama.com/library/qwen2.5-coder:7b-instruct

Freshness rule: Material changes set this stack to REVALIDATION_REQUIRED.