Another happy user here. Thanks @dingbatca for the great walkthrough!
On a gigabit cable connection (Comcast). With hardware offload, hitting in the mid 900's for download, right around 40 upload. Bufferbloat on downloads is staying under 20ms, and uploads ranges between 30 and 100.
With SQM enabled, hitting right at 200/40 but bufferbloat numbers aren't much better than the above (20-40 on average). So for now, staying with hardware offload.