Developer — Agentic Coding — RTX 4090
Current OpenHands guidance calls for at least 24 GB VRAM for quantized variants.
OpenHands
Open tool profile →Qwen3.6-35B-A3B
RTX 4090 24 GB / 64 GB RAM
GOOD_QUANTIZEDLocal inference configuration
Apache-2.0
Evidence
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.
Private AI Assistants
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.