Llama 4 Scout 17B-16E is a high-efficiency Mixture-of-Experts (MoE) model that
features 17 billion active parameters out of 109 billion total parameters and 16
experts.

Llama 4 Scout 17B-16E is suited for retrieval tasks within long contexts and
tasks that demand reasoning over large amounts of information, such as
summarizing multiple large documents, analyzing extensive user interaction logs
for personalization, and reasoning across large codebases.

## Managed API (MaaS) specifications


[Try in Agent Studio](https://console.cloud.google.com/agent-platform/generative/multimodal/create/text?model=llama-4-scout-17b-16e-instruct-maas)


[View model card in Model Garden](https://console.cloud.google.com/agent-platform/publishers/meta/model-garden/llama-4-maverick-17b-128e-instruct-maas)

| Model ID | `llama-4-scout-17b-16e-instruct-maas` ||
| Launch stage | GA ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Capabilities | - Supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/capabilities/batch-prediction.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/capabilities/function-calling.md.txt) - [Structured output](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/maas/capabilities/structured-output.md.txt) - Not supported - [Llama Guard](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/llama.md.txt) ||
| Usage types | - Supported - [Standard pay-as-you-go](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/standard-paygo.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) ||
| Knowledge cutoff date | August 2024 ||
| Versions | - `llama-4-scout-17b-16e-instruct-maas` - **Launch stage:** GA - **Release date:** April 29, 2025 ||
| Supported regions |
| Supported regions |
| Supported regions |
|---|---|---|
| Model availability | - United States - `us-east5` |
| ML processing | - United States - `Multi-region` |

## Deploy as a self-deployed model

To self-deploy the model, navigate to the [Llama 4 Scout 17B-16E model card](https://console.cloud.google.com/agent-platform/publishers/meta/model-garden/llama4) in the Model Garden
console and click **Deploy model**. When you self-deploy from
Model Garden, you can select from the following model variants:

- `llama-4-scout-17b-16e`: Pretrained model.

- `llama-4-scout-17b-16e-instruct`: Instruction-tuned model.

For more information about deploying and using partner models, see [Deploy a
partner model and make prediction
requests](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-garden/use-models#deploy_a_partner_model_and_make_prediction_requests).

## Considerations

Keep the following considerations in mind when using Llama 4 Scout 17B-16E:

- The managed MaaS endpoint (`llama-4-scout-17b-16e-instruct-maas`) serves the
  instruction-tuned model in fixed FP8 precision. You can't change the
  quantization format on the managed endpoint; to deploy a custom or
  pretrained variant, [self-deploy the model](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/llama/llama4-scout.md.txt#self-deploy) from
  Model Garden.

- You can include a maximum of three images per request.

- The MaaS endpoint doesn't use Llama Guard, unlike earlier Llama versions. To
  use Llama Guard, deploy Llama Guard from Model Garden and
  then send the prompts and responses to that endpoint. Compared to Llama 4,
  Llama Guard has a smaller context window (128,000 tokens) and only accepts
  requests with a single image at the beginning of the prompt.