← Back to Model Radar
#105 on the radar · Vision

sam3.1 ▼ 18

facebook · mask-generation
OlderVision
▲ 36Trending score
60kDownloads
♥ 675Likes
6 months agoLast updated
#105of 150 tracked models
top 70% by trending score
Model IDfacebook/sam3.1
Authorfacebook
Taskmask-generation
CategoryVision
Licenseother
Trending score36
Downloads60,479
Likes675
Radar rank#105
HealthOlder
Freshness6 months ago (168.8 days)
Last modified2026-03-27T17:40:55.000Z

sam3.1 is a mask-generation model in the Vision category, published by facebook. These figures are Hugging Face's own signals — downloads, likes and trending score — captured by Model Radar and refreshed daily. For weights, model card and usage, open it on Hugging Face.

Surge analysis

why it's on the radar

Hugging Face publishes a single trending score; it doesn't expose the formula. So Model Radar reads the surge from the four public signals that move with it — momentum, adoption, community and recency — each normalized against the tracked field, then weighted into a 0–100 composite. The weights are ours, and shown below. No hidden inputs.

50Radar surge index / 100
Momentum 48 / 100 · 45% weight
HF trending score 36, log-scaled vs the field's peak of 1763.
Adoption 57 / 100 · 25% weight
60k downloads, log-scaled vs the field's peak.
Community 68 / 100 · 18% weight
675 likes, log-scaled vs the field's peak.
Recency 15 / 100 · 12% weight
Last updated 6 months ago — newer weights higher.

Radar position over time

movement

Where sam3.1 sits on the radar, tracked daily — slipped 18 positions since the prior run. position over the last 11 days tracked · best: #81.

#105Current rank
#81Best rank
▼ 18Since prior run

In context

vs. category peers

How this model stacks up against the other 43 Vision models on the radar. The filled bar is this model; the tick is the category-peer median. Downloads and likes use a log scale (they span orders of magnitude).

Trending score▲ 36 · peer median ▲ 61
Downloads60k · peer median 330k
Likes♥ 675 · peer median ♥ 625
Freshness6 months ago · peer median 7 days ago

Bars are normalized against the most extreme model in the whole radar, so a near-full bar means category-leading. Peer median = the middle model of the 43 in this category.

Recency

last update

Where this model's last update lands on a freshness scale — fresh (<14d), recent (14–60d), or older.

updated 6 months ago
today14d60d1y+

Category peers

Vision · 43 models

Other Vision models ranked near this one — click through to compare.

📛 Embed this badge

rank badge

Show your live Model Radar rank in your README — it updates daily and links back here.

Model Radar rank badge for sam3.1

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/facebook-sam3-1.svg)](https://modelradar.kymatalabs.com/m/facebook-sam3-1/)
<a href="https://modelradar.kymatalabs.com/m/facebook-sam3-1/"><img src="https://modelradar.kymatalabs.com/badge/facebook-sam3-1.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

Go straight to the source — everything here links back to Hugging Face.