glance-vlm speedlab is now open source!
@yoheinakajima126K followers
51,739 views
27 Comments
Comments from the original post on X (Twitter)

@yoheinakajima
glance-vlm is a harness for measuring what happens when you chop off the generation from an open source vlm and use it as a classifier/decision model:
4 likes

@yoheinakajima
ICYMI that’s 161 ms latency on general vision true/false Qs at the end, running locally on webcam
8 likes

@yoheinakajima
compare glance 4B to laya-vision
3 likes

@assaf_elovic
Nice. One use case I see is to monitor elderly. My grandma is quite sick and it takes a lot of time, energy and attention to make sure she is good. Would be awesome to get an alert once the camera notices something weird in case we are not there. What do you think? Can be done?
1 like

@yoheinakajima
I think worth playing around with! Once you know a good use case you might want to go specialized but this is an easy way to prototype something quickly

@johnroodepic
for the temporal gate, compare against the last scored frame, not the previous camera frame. otherwise slow drift can stay below the threshold forever while the answer gets stale.
1 like

@yoheinakajima
hm thanks will take a look at this

@conikeec
Really neat . love it
1 like

@yoheinakajima
thx :)

@OpinionAILtd
This is game changer for vision AI
1 like

@tombielecki
🐐
1 like

@LShivkumarreddy
This is good!
1 like

@aroussi
This is awesome! I need to fork it and turn it to a meeting companion that helps neurodivergent people with reading emotions and social queues.
1 like

@kraayenJon
this is so cool!
1 like

@yoheinakajima
Thx :)
1 like

@rayane_esteves
210ms locally is the bit that jumps out, that puts weird webcam workflows in reach without renting a gpu every time. curious how hot the m 5 gets after 20 minutes though
1 like

@FantomKoenig
Agents got hands in 2023. Eyes took until 2026, at 260ms a glance. Counting people in a frame is arithmetic, a face is a guess. Which of your 21 failures surprised you most?

@joedevon
Great work Yohei!

@meimu7ns4
The interesting bit isn’t the webcam demo—it’s the loop shape. Turning a VLM into a cheap local decision engine is a much more useful product primitive than another chat wrapper.

@Mouten_dev
glance-vlmのspeedlab OSS、僕は触りたい。 webcamをローカル検出に、って相手の切り口は受け取る。 自分では未開。まずは






