Model Detail

paligemma-3b-pt-224 is a multimodal model with 3B parameters released by Google. The model is registered under the image-text-to-text pipeline tag on Hugging Face, released under the gemma license.

paligemma-3b-pt-224 ships with 3B parameters. Total weight footprint is approximately 2.9 GB, which is the relevant figure when planning local-inference VRAM. Access is gated on Hugging Face under the gemma license, which means a manual approval step before weights can be downloaded.

paligemma-3b-pt-224 is best fit for mixed text-and-image reasoning tasks such as document understanding. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.