Skip navigation
all three at a time, down to less than 1 sec latency
0:00 / 0:26

all three at a time, down to less than 1 sec latency

Yohei

@yoheinakajima126K followers

Visit on X
23 likesDownloadOriginal post

19,486 views

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

9 Comments

Comments from the original post on X (Twitter)

  • Yohei's profile picture

    @yoheinakajima

    got object detection down to below 0.35 sec latency locally

    9 likes

  • Yohei's profile picture

    @yoheinakajima

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

    2 likes

  • Yohei's profile picture

    @yoheinakajima

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

    4 likes

  • Yohei's profile picture

    @yoheinakajima

    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

    4 likes

  • Yohei's profile picture

    @yoheinakajima

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

    95 likes

  • Yohei's profile picture

    @yoheinakajima

    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

    9 likes

  • Mo ShaRaf (sharaf.eth)'s profile picture

    @MSharafH

    Which model is this?

    1 like

  • Yohei's profile picture

    @yoheinakajima

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

    4 likes

  • ethereagle · building's profile picture

    @ethereaglehq

    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?