Downloads · 30 days
23
11% of all-time downloads
nanovdr/NanoVDR-Q-BERT-Qwen3VL2B-2048-ML
NanoVDR-Q-BERT-Qwen3VL2B-2048-ML is a sentence similarity model from nanovdr. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as apache-2.0.
Paper: NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval | Blog | Project page
Downloads · 30 days
23
11% of all-time downloads
All-time downloads
201
Public
Repo size
447 MB
Likes
1
Public
Click a slice to open those files.
.safetensors438 MB · 98%
From the Hugging Face model README
Paper: NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval | Blog | Project page
⚠️ This model was renamed
It was published as
nanovdr/NanoVDR-M-Multi. Old links andfrom_pretrainedcalls still resolve through a redirect, but please move to the new id.- SentenceTransformer("nanovdr/NanoVDR-M-Multi") + SentenceTransformer("nanovdr/NanoVDR-Q-BERT-Qwen3VL2B-2048-ML")Why. NanoVDR started as one thing: a small text encoder that replaces the query side of a large vision-language retriever. It has since grown a second tower that replaces the document side, and a second teacher, so a name like
-Sno longer says enough. Two checkpoints only work together when they were distilled from the same teacher into the same width, and neither fact was recoverable from the old names.The scheme is now
NanoVDR-<Q|D>-<variant>-<teacher>-<width>[-ML], and the rule is simply that the teacher and the width have to match. This model isQ(query tower),BERT(backbone), distilled from Qwen3-VL-Embedding-2B into 2048 dimensions, trained on the multilingual mixture (-ML).-MLused to be spelled-Multi, which read as multi-vector when it meant multilingual.
NanoVDR-Q-BERT-Qwen3VL2B-2048-ML is a 116M-parameter multilingual text-only query encoder for visual document retrieval. It retrieves document page images as effectively as Vision-Language Models 30-100x its size, with strong cross-lingual transfer across 6 languages.
Built on NanoVDR-Q-DistilBERT-Qwen3VL2B-2048 and further trained with multilingual query augmentation (English + German, French, Spanish, Italian, Portuguese), it is the recommended model for production use with multilingual or mixed-language queries.
| Model | Params | ViDoRe v1 (en) | ViDoRe v2 (multi) | ViDoRe v3 (multi) |
|---|---|---|---|---|
| Qwen3-VL-Emb (Teacher) | 2.0B | 84.3 | 65.3 | 50.0 |
| NanoVDR-Q-BERT-Qwen3VL2B-2048-ML | 112M | 82.5 | 62.8 | 47.5 |
| NanoVDR-Q-DistilBERT-Qwen3VL2B-2048-ML | 69M | 82.2 | 61.9 | 46.5 |
| ColPali | ~3B | 84.2 | 54.7 | 42.0 |
| Language | NDCG@5 | Teacher Retention |
|---|---|---|
| English | 50.7 | 93.0% |
| French | 47.8 | 93.6% |
| Spanish | 47.8 | 93.1% |
| Italian | 45.7 | 93.3% |
| German | 45.4 | 92.0% |
| Portuguese | 46.1 | 94.6% |
All 6 languages achieve >92% of the 2B teacher's performance.
NanoVDR decouples query encoding from document encoding in visual document retrieval:
Retrieval uses standard cosine similarity between query and document embeddings.
from sentence_transformers import SentenceTransformer
# Load the multilingual query encoder
model = SentenceTransformer("nanovdr/NanoVDR-Q-BERT-Qwen3VL2B-2048-ML")
# Encode queries in any supported language
queries = [
"What was the revenue growth in Q3 2024?", # English
"Quel est le chiffre d'affaires du trimestre?", # French
"Wie hoch war das Umsatzwachstum im dritten Quartal?", # German
"Cual fue el crecimiento de ingresos en el Q3?", # Spanish
]
query_embeddings = model.encode(queries)
print(query_embeddings.shape) # (4, 2048)
# Retrieve against pre-indexed document embeddings from the VLM teacher
# scores = query_embeddings @ doc_embeddings.T
from sentence_transformers import SentenceTransformer
# Step 1: Index documents with the VLM teacher (one-time, offline)
from transformers import AutoModel
teacher = AutoModel.from_pretrained("Qwen/Qwen3-VL-Embedding-2B")
# doc_embeddings = teacher.encode(document_images) # See Qwen3-VL-Embedding docs
# Step 2: Query with NanoVDR-Q-DistilBERT-Qwen3VL2B-2048-ML (online, fast, CPU-only)
student = SentenceTransformer("nanovdr/NanoVDR-Q-BERT-Qwen3VL2B-2048-ML")
query_emb = student.encode("Quel est le chiffre d'affaires?")
# Step 3: Retrieve
scores = query_emb @ doc_embeddings.T
top_k = scores.argsort()[-5:][::-1]
Every model in this table targets Qwen3-VL-Embedding-2B at 2048 dimensions, so documents still have to be indexed by that 2B teacher. A second family targets the 8B teacher at 4096 dimensions and includes a document tower, so nothing multi-billion runs at indexing time either:
| Model | Role | Params |
|---|---|---|
| NanoVDR-Q-DistilBERT-Qwen3VL8B-4096-ML | query tower | 70M |
| NanoVDR-D-HiRes-Qwen3VL8B-4096 | document tower | 457M |
| NanoVDR-D-Fast-Qwen3VL8B-4096 | document tower, 3x fewer visual tokens | 457M |
The two families are not interchangeable: 2048-d and 4096-d vectors live in different spaces and will not score against each other.
| Metric | NanoVDR-Q-BERT-Qwen3VL2B-2048-ML | ColPali (3B) | Teacher (2B) |
|---|---|---|---|
| Query latency (CPU, B=1) | 51 ms | 7,300 ms | GPU only |
| Model size | 116M | ~3B | 2B |
| Index type | Single-vector | Multi-vector | Single-vector |
| Scoring | Cosine | MaxSim | Cosine |
@article{nanovdr2026,
title={NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval},
author={Liu, Zhuchenyang and Zhang, Yao and Xiao, Yu},
journal={arXiv preprint arXiv:2603.12824},
year={2026}
}
Apache 2.0