← Catalog

vidore/colpali-v1.3-hf

Add to compare Open comparison →

Primitive: /encode · Encode · PaliGemma

> [!IMPORTANT] > This version of ColPali should be loaded with the `transformers 🤗` release, not with `colpali-engine`. > It was converted using the `convert_colpali_weights_to_hf.py` script > from the `vidore/colpali-v1.3-merged` checkpoint.

View on Hugging Face → Fine-tuned from vidore/colpaligemma-3b-pt-448-base

Overview

Hardware: L4RTX-PRO-6000 — drives latency, throughput & cost

Size	3.0B params
Tasks	/encode
License	gemma
Languages	en
Latency	582 ms
Throughput	23.0 mpix/s
Cost	— /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Embedding

Output types	Multi-Vec
Dimensions	multivector: 128
Max sequence length	2,048
Inputs	text · image

Benchmarks