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

JEV-27B-VL

autotrust · image-text-to-text
FreshFresh (<14d)Vision
▲ 49Trending score
179kDownloads
♥ 50Likes
todayLast updated
#92of 150 tracked models
top 61% by trending score
Model IDautotrust/JEV-27B-VL
Authorautotrust
Taskimage-text-to-text
CategoryVision
Licenseapache-2.0
Parameters27.8B
Trending score49
Downloads179,237
Likes50
Radar rank#92
HealthFresh (<14d)
Freshnesstoday (0.2 days)
Last modified2026-10-02T12:06:07.000Z

JEV-27B-VL is a image-text-to-text model in the Vision category, published by autotrust. 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.

60Radar surge index / 100
Momentum 56 / 100 · 45% weight
HF trending score 49, log-scaled vs the field's peak of 1095.
Adoption 63 / 100 · 25% weight
179k downloads, log-scaled vs the field's peak.
Community 40 / 100 · 18% weight
50 likes, log-scaled vs the field's peak.
Recency 99 / 100 · 12% weight
Last updated today — newer weights higher.

Radar position over time

movement

Where JEV-27B-VL sits on the radar, tracked daily — new to the radar since the prior run. position movement fills in as the radar refreshes daily.

#92Current rank
#92Best rank
NEWSince prior run

In context

vs. category peers

How this model stacks up against the other 48 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▲ 49 · peer median ▲ 64
Downloads179k · peer median 159k
Likes♥ 50 · peer median ♥ 466
Freshnesstoday · 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 48 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 today
today14d60d1y+

Category peers

Vision · 48 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 JEV-27B-VL

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/autotrust-jev-27b-vl.svg)](https://modelradar.kymatalabs.com/m/autotrust-jev-27b-vl/)
<a href="https://modelradar.kymatalabs.com/m/autotrust-jev-27b-vl/"><img src="https://modelradar.kymatalabs.com/badge/autotrust-jev-27b-vl.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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