Google · Official-source model record
paligemma2 3b mix 224
paligemma · Version google/paligemma2-3b-mix-224
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about paligemma2 3b mix 224
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which paligemma2 3b mix 224 does this page describe?
paligemma2 3b mix 224 is a model record from Google in the paligemma family. Source
The recorded model identifier or checkpoint is google/paligemma2-3b-mix-224. Use that exact identifier when checking documentation or a provider listing. Source
How can you access paligemma2 3b mix 224?
The catalog documents Open weights access for paligemma2 3b mix 224. Source
As of the catalog check, this version was listed as available. Source
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement.
What can paligemma2 3b mix 224 receive and generate?
Documented inputs: Text and Image. Source
Documented outputs: Text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for paligemma2 3b mix 224?
The recorded license label is gemma. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What distinguishes paligemma2 3b mix 224?
These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.
- Checkpoint resolution and training stage
- Publisher's 3B checkpoint. Tuned on a mixture of academic tasks. Uses 224×224 input images. Source
- Output formats
- Produces text, including captions, answers, object bounding-box coordinates or segmentation codewords. Source
- Architecture
- Combines a Gemma 2 language decoder with a SigLIP-So400m/14 vision encoder. Source
What is documented about the paligemma2 3b mix 224 checkpoint?
This evidence refers to google/paligemma2-3b-mix-224 at recorded revision 8e40ab4cc5df93dfb7fd2fff754bcdff8b62ee78, checked October 23, 2026. Repository metadata
Safetensors metadata records 3,032,242,416 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: PaliGemmaForConditionalGeneration. Repository metadata
Repository task tag: image-text-to-text. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata
Repository access gate: manual. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other paligemma models from Google.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
paligemma 3b mix 224
Open weights
paligemma 3b mix 448
Open weights
paligemma 3b pt 224
Open weights
paligemma 3b pt 448
Open weights
paligemma 3b pt 896
Open weights
paligemma2 10b mix 224
Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- GoogleSource ↗
- Family
- paligemmaSource ↗
- Version
- google/paligemma2-3b-mix-224Source ↗
- Availability
- AvailableSource ↗
- Access
- Open weightsSource ↗
- Inputs
- Text · ImageSource ↗
- Outputs
- TextSource ↗
- Context window
- Not documented
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Not documented
- License
- gemmaSource ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official Google-published checkpoint. Base/pretrained and instruction-tuned variants remain distinct; platform and quantized packaging copies are excluded. Hosted API availability not inferred. Publisher repository evidence (2026-10-23): Publisher task label: image-text-to-text. Published architecture metadata: PaliGemmaForConditionalGeneration. Repository library label: transformers. Published safetensors metadata counts 3,032,242,416 stored parameters; this is not an active-parameter count for mixture-of-experts models. Repository access metadata is manual; access gating does not establish license permissions.
Model identifiers and aliases 0
No additional identifier has been verified.
Follow the evidence