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

Hy4-preview ▼ 64

tencent · text-generation
Recently updatedText
▲ 28Trending score
8.9kDownloads
♥ 468Likes
15 days agoLast updated
#141of 150 tracked models
top 94% by trending score
Model IDtencent/Hy4-preview
Authortencent
Tasktext-generation
CategoryText
Licenseapache-2.0
Parameters780B
Trending score28
Downloads8,936
Likes468
Radar rank#141
HealthRecently updated
Freshness15 days ago (14.9 days)
Last modified2026-08-28T14:58:32.000Z

Hy4-preview 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 45 / 100 · 45% weight
HF trending score 28, log-scaled vs the field's peak of 1763.
Adoption 47 / 100 · 25% weight
8.9k downloads, log-scaled vs the field's peak.
Community 64 / 100 · 18% weight
468 likes, log-scaled vs the field's peak.
Recency 67 / 100 · 12% weight
Last updated 15 days ago — newer weights higher.

Radar position over time

movement

Where Hy4-preview sits on the radar, tracked daily — slipped 64 positions since the prior run. position over the last 16 days tracked · best: #6.

#141Current rank
#6Best rank
▼ 64Since prior run

In context

vs. category peers

How this model stacks up against the other 47 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▲ 28 · peer median ▲ 44
Downloads8.9k · peer median 26k
Likes♥ 468 · peer median ♥ 349
Freshness15 days ago · peer median 5 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 47 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 15 days ago
today14d60d1y+

Category peers

Text · 47 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 Hy4-preview

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/tencent-hy4-preview.svg)](https://modelradar.kymatalabs.com/m/tencent-hy4-preview/)
<a href="https://modelradar.kymatalabs.com/m/tencent-hy4-preview/"><img src="https://modelradar.kymatalabs.com/badge/tencent-hy4-preview.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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