Sa2VA 4B Video

Name: Sa2VA 4B Video
Author: fal

other

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Capabilities

Show unsupported (8)

No supported capabilities recorded.

Model IDfal-ai/sa2va/4b/video

Providerfal

Creatorfal

Family—

License—

Statusactive

Typeother

Input modalitiesimage

Output modalities—

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date2025-01-13

Sourceofficial

GET/v1/models/fal/fal-ai/sa2va/4b/video

fal-ai/sa2va/4b/video

Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels

Changes · 2 entries

fal-ai/sa2va/4b/videocreateca7a400Nov 2, 2026, 03:02 AM

fal-ai/sa2va/4b/videocreate08f0ffeMay 11, 2026, 08:27 AM