# MiniMax publishes VTP-Base image feature extraction model

> MiniMax published VTP-Base-f16d64 on Hugging Face, an image-feature-extraction model under the VTP family (referenced by arxiv:2512.13687). The repository provides no capability or benchmark details beyond pipeline tags.

| | |
|---|---|
| **Tool** | MiniMax |
| **Version** | — |
| **Kind** | release |
| **Published** | 2025-12-16 |
| **Observed** | 2026-08-11 |
| **Significance** | 1/5 |
| **Breaking** | no |
| **Categories** | model-support |

> **Note:** this classification is below our confidence threshold and is pending human review.

## What changed


Model published on Hugging Face under MiniMaxAI organisation.
- Pipeline: image-feature-extraction
- Library: transformers
- Tags: vtp, safetensors, arxiv:2512.13687, endpoints_compatible
- License: other


## Sources

- [hf_model](https://huggingface.co/MiniMaxAI/VTP-Base-f16d64) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/minimax/minimax-publishes-vtp-base-image-feature-extraction-model
Entity: https://changelogs.info/minimax
Event ID: `evt_2025-12-16_minimax_minimaxai-vtp-base-f16d64`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.