Tencent open-sources EVIE visual document retrieval models

Tencent

Models / LLM official 3 src. ~1 min

Tencent released EVIE-8B and EVIE-4.5B, visual document retrieval models built on Qwen3.5 backbones using late-interaction (ColBERT-style) multi-vector embeddings over document page images. EVIE-8B ranks #1 on ViDoRe V3 at 66.75 nDCG@10, with EVIE-4.5B ranking #2 at 66.02; both ship under Apache-2.0 with training and distillation code on GitHub. The 4.5B student supports runtime truncation of its 2048D projection head down to 64D, reducing index size.

Why it matters

First open models to top the ViDoRe visual document retrieval leaderboard, meaning genuinely usable open document-RAG for enterprise pipelines.

Importance: 3/5

Notable open-weights release topping a public retrieval leaderboard

retrieval embedding open-source vision-language

Sources

official EVIE-8B model card (Hugging Face)

official EVIE-4.5B model card (Hugging Face)

official Tencent/EVIE GitHub repository