← Back to Model Radar
#97 on the radar · Other

MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA

lightx2v · —
FreshFresh (<14d)Other
▲ 57Trending score
13kDownloads
♥ 58Likes
4 days agoLast updated
#97of 150 tracked models
top 65% by trending score
Model IDlightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA
Authorlightx2v
Task—
CategoryOther
Parameters27.4B
Trending score57
Downloads12,763
Likes58
Radar rank#97
HealthFresh (<14d)
Freshness4 days ago (4.2 days)
Last modified2026-10-29T15:04:45.000Z

MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA is a — model in the Other category, published by lightx2v. 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.

59Radar surge index / 100
Momentum 62 / 100 · 45% weight
HF trending score 57, log-scaled vs the field's peak of 719.
Adoption 55 / 100 · 25% weight
13k downloads, log-scaled vs the field's peak.
Community 41 / 100 · 18% weight
58 likes, log-scaled vs the field's peak.
Recency 88 / 100 · 12% weight
Last updated 4 days ago — newer weights higher.

Radar position over time

movement

Where MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA sits on the radar, tracked daily — new to the radar since the prior run. position movement fills in as the radar refreshes daily.

#97Current rank
#97Best rank
NEWSince prior run

In context

vs. category peers

How this model stacks up against the other 30 Other 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▲ 57 · peer median ▲ 63
Downloads13k · peer median 12k
Likes♥ 58 · peer median ♥ 262
Freshness4 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 30 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

Other · 30 models

Other Other 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 MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA

[![Model Radar rank](https://modelradar.kymatalabs.com/badge/lightx2v-minimax-h3-prompt-rewriter-qwen3-8-27b-ref2va.svg)](https://modelradar.kymatalabs.com/m/lightx2v-minimax-h3-prompt-rewriter-qwen3-8-27b-ref2va/)
<a href="https://modelradar.kymatalabs.com/m/lightx2v-minimax-h3-prompt-rewriter-qwen3-8-27b-ref2va/"><img src="https://modelradar.kymatalabs.com/badge/lightx2v-minimax-h3-prompt-rewriter-qwen3-8-27b-ref2va.svg" alt="Model Radar rank"></a>

Primary links

on hugging face

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