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

DeepSeek-V4-Flash-0731 ▼ 18

deepseek-ai · text-generation
Recently updatedText
▲ 36Trending score
4.4MDownloads
♥ 3.9kLikes
1 month agoLast updated
#107of 150 tracked models
top 71% by trending score
Model IDdeepseek-ai/DeepSeek-V4-Flash-0731
Authordeepseek-ai
Tasktext-generation
CategoryText
Licensemit
Parameters304B
Trending score36
Downloads4,374,129
Likes3,933
Radar rank#107
HealthRecently updated
Freshness1 month ago (42.4 days)
Last modified2026-08-01T03:07:41.000Z

DeepSeek-V4-Flash-0731 is a text-generation model in the Text category, published by deepseek-ai. 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.

62Radar surge index / 100
Momentum 48 / 100 · 45% weight
HF trending score 36, log-scaled vs the field's peak of 1763.
Adoption 79 / 100 · 25% weight
4.4M downloads, log-scaled vs the field's peak.
Community 86 / 100 · 18% weight
3.9k likes, log-scaled vs the field's peak.
Recency 41 / 100 · 12% weight
Last updated 1 month ago — newer weights higher.

Radar position over time

movement

Where DeepSeek-V4-Flash-0731 sits on the radar, tracked daily — slipped 18 positions since the prior run. position over the last 43 days tracked · best: #2.

#107Current rank
#2Best rank
▼ 18Since 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▲ 36 · peer median ▲ 44
Downloads4.4M · peer median 26k
Likes♥ 3.9k · peer median ♥ 349
Freshness1 month 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 1 month 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 DeepSeek-V4-Flash-0731

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/deepseek-ai-deepseek-v4-flash-0731.svg)](https://modelradar.kymatalabs.com/m/deepseek-ai-deepseek-v4-flash-0731/)
<a href="https://modelradar.kymatalabs.com/m/deepseek-ai-deepseek-v4-flash-0731/"><img src="https://modelradar.kymatalabs.com/badge/deepseek-ai-deepseek-v4-flash-0731.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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