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

Hy-MT2-30B-A3B ▼ 14

tencent · translation
FreshFresh (<14d)Text
▲ 32Trending score
5.5kDownloads
♥ 448Likes
10 days agoLast updated
#81of 150 tracked models
top 54% by trending score
Model IDtencent/Hy-MT2-30B-A3B
Authortencent
Tasktranslation
CategoryText
Trending score32
Downloads5,479
Likes448
Radar rank#81
HealthFresh (<14d)
Freshness10 days ago (9.7 days)
Last modified2026-05-26T09:05:48.000Z

Hy-MT2-30B-A3B is a translation model in the Text category, published by tencent. 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.

54Radar surge index / 100
Momentum 50 / 100 · 45% weight
HF trending score 32, log-scaled vs the field's peak of 1026.
Adoption 44 / 100 · 25% weight
5.5k downloads, log-scaled vs the field's peak.
Community 64 / 100 · 18% weight
448 likes, log-scaled vs the field's peak.
Recency 76 / 100 · 12% weight
Last updated 10 days ago — newer weights higher.

Radar position over time

movement

Where Hy-MT2-30B-A3B sits on the radar, tracked daily — slipped 14 positions since the prior run. position over the last 5 days tracked · best: #14.

#81Current rank
#14Best rank
▼ 14Since 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▲ 32 · peer median ▲ 30
Downloads5.5k · peer median 85k
Likes♥ 448 · peer median ♥ 392
Freshness10 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 10 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 Hy-MT2-30B-A3B

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/tencent-hy-mt2-30b-a3b.svg)](https://modelradar.kymatalabs.com/m/tencent-hy-mt2-30b-a3b/)
<a href="https://modelradar.kymatalabs.com/m/tencent-hy-mt2-30b-a3b/"><img src="https://modelradar.kymatalabs.com/badge/tencent-hy-mt2-30b-a3b.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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