Back to Model
V

VIGOR-27B

Model Nov 2, 2026

An independent 27B multimodal model for conservative Safe/NSFW image classification with structured JSON output, described by its author as based on Qwen3.8-27B.

Visit primary link 2 sources attached
VIGOR 27b announcement banner from prithivMLmods, labeled Safety Classification.
Author-published VIGOR-27B announcement artwork from the English model card. This is release branding, not a classification example or evidence of model accuracy. Source: prithivMLmods
self-hosted

What happened lately

VIGOR-27B timeline

VIGOR-27B is prithivMLmods’ independent image-moderation release. Its English card describes a dense 27B model based on Qwen3.8-27B, with a strict Safe/NSFW policy and structured scene descriptions. The weight upload is dated November 1, 2026; subsequent card edits are documentation updates.

The card provides a Transformers quick start and labels the release Apache 2.0, subject to applicable base and component terms. It warns that benign imagery may be flagged and unsafe imagery may be missed. AITrending has not run the model or verified the author’s accuracy and speculative-decoding claims.