all three at a time, down to less than 1 sec latency - expression - object detection - finger count

got object detection down to below 0.35 sec latency locally

live true/false on object detection is at 0.4 seconds latency locally on an M5 macbook pro

just object detection is much faster with .5 sec latency much snappier

same thing, this time running locally. inference is slower, but no network latency (above was via replicate) inference: 1.1 sec seems inference time goes up with number of possible answers, and here's that's about 14 across three questions

simultaneous live detection of: 😡 emotion 📕 object 🖐️ finger count single call for 3 detections, 0.2 sec inference each

all three at a time sub 0.5 second latency! - expression - object detection - finger count switched to qwen 8B via glance i think direct on MLX

Which model is this?

qwen3-vl-4b via glance (no generation)

sub 1s for expression + objects + fingers. did you pack all three into one call, or are they still separate and the model just got faster?