GUIDE BY CAPACITY
With 33–48 GB,
here is what really runs.
Experiences reported by people using their machines every day. The figure is the reported setup capacity; multi-GPU and unified-memory layouts can behave differently.
2documented uses
in this range
in this range
Coding
A senior engineer with no need for cloud on a 64GB Strix Halo
An experienced software engineer runs Qwen3-Coder 30B on a 64GB Strix Halo and finds local working better than newer, larger models for well-scoped tasks.
Coding
Qwen 27B coding and infrastructure on two 3090s
A two-3090 local setup runs Qwen 27B for coding and infrastructure work, including bug fixing and quality-of-life automation.