# Hugging Face — NeoMME: an efficient Multimodal-native and Multilingual Encoder

- Company: Hugging Face (huggingface.co)
- Announced: 2026-09-03T13:13:48+00:00
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/Hcompany/neomme
- Record: https://forck.live/items/7637-neomme-an-efficient-multimodal-native-and-multilingual-encoder
- Subject: Platform
- Open weights: yes
- Models affected: NeoMME, NeoMME -Retriever
- License: Apache 2.0
- Context window: 16,384 tokens

Hugging Face introduces NeoMME, a family of 260M and 800M multilingual multimodal encoders trained from scratch with a masked discrete-diffusion objective. The model is fine-tuned for visual document retrieval and achieves high throughput. All model checkpoints are released under the Apache 2.0 license.

## Evidence

Verbatim from https://huggingface.co/blog/Hcompany/neomme:

> We introduce NeoMME , a family of 260M and 800M multilingual multimodal encoders.

---

Record: https://forck.live/items/7637-neomme-an-efficient-multimodal-native-and-multilingual-encoder
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md