AxForge
Sign in Get started

Model reference · open weights

paligemma-pt-224

LLMs google Vision + text 1 build Open, with conditions 204k dl/mo

paligemma-pt-224 is an open-weight language model from Google. paligemma-3b-pt-224 (FP32) weighs 5.8 GB; the smallest configuration that runs it is RTX 3060 12 GB.

  • PaliGemma is a 2.9 billion parameter vision-language model developed by Google that processes 224x224 pixel images and 128 token text sequences to generate text outputs.
  • It is designed for fine-tuning on tasks such as image captioning, visual question answering, and object detection, and supports multiple languages.
  • The model is released under the Gemma license and is available in float32, bfloat16, and float16 formats.

Summary of the google/paligemma-3b-pt-224 model card, 2026-10-01

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released byGoogle
Released2024-05-12
Parameters2.9B
VRAM5.8 GB for the weights

What it runs on

Memory and cards for paligemma-3b-pt-224 (FP32)

5.8 GBweights, file size
762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

CardWeights alone
RTX 3060 12 GBfits
RTX 4060 Ti 16 GBfits
RTX 3090 24 GBfits
RTX 4090 24 GBfits
RTX 5090 32 GBfits
L40S 48 GBfits
A100 80 GBfits
H100 80 GBfits
RTX PRO 6000 Blackwell 96 GBfits
DGX Spark (GB10) 128 GB unifiedfits
H200 141 GBfits
B200 180 GBfits

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms