PaliGemma models
3 PaliGemma models from Google on Hugging Face, from 2.9B to 2.9B parameters, published by Google in F32. The smallest official model, paligemma-3b-mix-224, needs about 13.1 GB of VRAM at its published precision; the cheapest live fit is V100 at $0.110/hr.
Part of the Gemma series
Pick a size
One row per official PaliGemma size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| paligemma-3b-pt-224 | 2.9B | 13.1 GB | 3.3 GB | 1.6 GB | V100 | $0.110/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| paligemma-3b-mix-224 | 2.9B | F32 | 13.1 GB | V100 | $0.110/hr |
| paligemma-3b-pt-224 | 2.9B | F32 | 13.1 GB | V100 | $0.110/hr |
Fine-tunes and community models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| paligemma-3b-ft-cococap-448 | 2.9B | F32 | 13.1 GB | V100 | $0.110/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from Google
Related on Aquanode: GPU requirements for paligemma-3b-pt-224.