← Back to Model Radar
#48 on the radar · Text

Mellum2-12B-A2.5B-Instruct

JetBrains · text-generation
FreshFresh (<14d)Text
▲ 48Trending score
1.4kDownloads
♥ 48Likes
4 days agoLast updated
#48of 150 tracked models
top 32% by trending score
Model IDJetBrains/Mellum2-12B-A2.5B-Instruct
AuthorJetBrains
Tasktext-generation
CategoryText
Trending score48
Downloads1,418
Likes48
Radar rank#48
HealthFresh (<14d)
Freshness4 days ago (3.6 days)
Last modified2026-06-01T11:16:56.000Z

Mellum2-12B-A2.5B-Instruct is a text-generation model in the Text category, published by JetBrains. 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.

53Radar surge index / 100
Momentum 56 / 100 · 45% weight
HF trending score 48, log-scaled vs the field's peak of 1026.
Adoption 37 / 100 · 25% weight
1.4k downloads, log-scaled vs the field's peak.
Community 41 / 100 · 18% weight
48 likes, log-scaled vs the field's peak.
Recency 89 / 100 · 12% weight
Last updated 4 days ago — newer weights higher.

Radar position over time

movement

Where Mellum2-12B-A2.5B-Instruct sits on the radar, tracked daily — held position since the prior run. position over the last 4 days tracked · best: #48.

#48Current rank
#48Best rank
Since prior run

In context

vs. category peers

How this model stacks up against the other 32 Text 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▲ 48 · peer median ▲ 30
Downloads1.4k · peer median 85k
Likes♥ 48 · peer median ♥ 392
Freshness4 days ago · peer median 10 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 32 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 4 days ago
today14d60d1y+

Category peers

Text · 32 models

Other Text 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 Mellum2-12B-A2.5B-Instruct

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/jetbrains-mellum2-12b-a2-5b-instruct.svg)](https://modelradar.kymatalabs.com/m/jetbrains-mellum2-12b-a2-5b-instruct/)
<a href="https://modelradar.kymatalabs.com/m/jetbrains-mellum2-12b-a2-5b-instruct/"><img src="https://modelradar.kymatalabs.com/badge/jetbrains-mellum2-12b-a2-5b-instruct.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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