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

Hy3 ▼ 29

tencent · text-generation
FreshFresh (<14d)Text
▲ 26Trending score
21kDownloads
♥ 885Likes
8 days agoLast updated
#115of 150 tracked models
top 77% by trending score
Model IDtencent/Hy3
Authortencent
Tasktext-generation
CategoryText
Licenseapache-2.0
Parameters299B
Trending score26
Downloads20,731
Likes885
Radar rank#115
HealthFresh (<14d)
Freshness8 days ago (8.2 days)
Last modified2026-07-20T07:01:39.000Z

Hy3 is a text-generation 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.

52Radar surge index / 100
Momentum 37 / 100 · 45% weight
HF trending score 26, log-scaled vs the field's peak of 6913.
Adoption 51 / 100 · 25% weight
21k downloads, log-scaled vs the field's peak.
Community 71 / 100 · 18% weight
885 likes, log-scaled vs the field's peak.
Recency 79 / 100 · 12% weight
Last updated 8 days ago — newer weights higher.

Radar position over time

movement

Where Hy3 sits on the radar, tracked daily — slipped 29 positions since the prior run. position over the last 22 days tracked · best: #1.

#115Current rank
#1Best rank
▼ 29Since prior run

In context

vs. category peers

How this model stacks up against the other 56 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▲ 26 · peer median ▲ 39
Downloads21k · peer median 32k
Likes♥ 885 · peer median ♥ 188
Freshness8 days ago · peer median 6 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 56 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 8 days ago
today14d60d1y+

Category peers

Text · 56 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 Hy3

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/tencent-hy3.svg)](https://modelradar.kymatalabs.com/m/tencent-hy3/)
<a href="https://modelradar.kymatalabs.com/m/tencent-hy3/"><img src="https://modelradar.kymatalabs.com/badge/tencent-hy3.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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