Tencent EVIE-Preview-4.5B tops ViDoRe V3 with compact 128-dim multilingual visual document retrieval

Tencent

Tools official + media 1 src. ~1 min

EVIE-Preview-4.5B is a multilingual visual document retrieval model built on Qwen3.5-4B (ColBERT-style late interaction, interleaved Gated DeltaNet with full attention) producing 128-dim multi-vector token embeddings. It scores 64.40 nDCG@10 average on ViDoRe V3 (leading 7 of 8 domains) and 85.93 average on ViDoRe V1 plus V2, covering EN, FR, DE, IT, ES, PT, ZH.

Why it matters

Compact 4.5B VDR model that beats 8B-class competitors while staying compatible with the existing colpali-engine pipeline, so it slots into production retrieval stacks with minimal infra changes; the preview status implies a v1 to follow.

Importance: 3/5

open-weights / GA marker

Sources