Back to News
Advertisement
ccleardusk about 5 hours ago 13 commentsRead Article on github.com

FR version is available. Content is displayed in original English for accuracy.

The model has 3B active parameters. We put the code, homepage, paper and model links here:

- Code: https://github.com/bytedance/Lance

- Homepage: https://lance-project.github.io/

- Paper: https://arxiv.org/abs/2605.18678

- Model: https://huggingface.co/bytedance-research/Lance

p.s. Lance is a research project, not a polished product. The model was trained using fewer than 128 GPUs.

Advertisement

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 216 words in the discussion.

Trending Topics

#model#video#active#silly#little#slop#seems#resolution#frame#micro

Discussion (13 Comments)Read Original on HackerNews

bguberfain44 minutes ago
Any plans to port to sglang or vLLM?
nkvdevabout 1 hour ago
Great quality, forked and going to try
popalchemistabout 2 hours ago
Seems like the video output is crippled. Resolution is low (720 or so), as is the frame rate. The samples are shown up-scaled and frame-interpolated.

Why do that? Seems strange to be building sub-hd resolution video models in 2026.

jadboxabout 1 hour ago
Sure, but again, it's a micro 3B model. Perhaps it can't be used for general video work, but it might be able to do basic edits like remove an object from a table in a shot.
MattRix40 minutes ago
It’s not a micro model at all, it requires 40gb of VRAM. The 3B is just the active parameters.
Tsarpabout 4 hours ago
Nice work. Wish they had picked another name given how popular lance/lancedb is.
CrzyLngPwdabout 3 hours ago
Imagine having virtually unlimited compute and programming resources, and silly little slop videos is the result.

Fabulous.

menno-shabout 2 hours ago
Not that surprising if the reason you have virtually unlimited compute and programming resources is that you work at the leading short form video app company. They could also have chosen nót to open source it.
neosatabout 1 hour ago
Do you find the video understanding work there also to be 'silly little slop', or did you only look at the gifs on the page and not read about the understanding work in a 3B model?

This is not ground-breaking by any means, but achieving this in a 3B model and sharing the approach + weights advances engineering and certainly more contribution that 'silly little slop videos' imo.

MattRix39 minutes ago
It’s not a 3B model, it has 3B active parameters. The full model is much larger.
neosat8 minutes ago
That's true, I should have mentioned active. Actual params are closer to 12B-14B likely, given the 40GB VRAM usage.
asadmabout 4 hours ago
last dance for lance vance!
clearduskabout 3 hours ago
:D