> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/compute/limits-and-concurrency.md).

# Limits and concurrency

The limits on block runs, and how many can run at once.

## Run time

| Limit             | Value      |
| ----------------- | ---------- |
| **Any block run** | 12 hours   |
| **Lambda blocks** | 15 minutes |

## Memory and storage

| Compute type                            | Memory                                            | Scratch storage         |
| --------------------------------------- | ------------------------------------------------- | ----------------------- |
| **Lambda**                              | 10 GB                                             | 10 GB                   |
| **Fargate**                             | Up to 120 GB, with up to 16 CPUs                  | 20 to 200 GB            |
| **GPU**                                 | Depends on the instance                           | Depends on the instance |
| **Kubernetes and Armada** (self-hosted) | Set per block, within your administrators' limits | Up to 200 GB            |

## Concurrency

There's a limit on how many block runs can happen at once.

| Limit                | Default                                                                          |
| -------------------- | -------------------------------------------------------------------------------- |
| **Per organization** | 100 block runs at once. It can be set between 1 and 1,000 for your organization. |
| **Per user**         | 100 block runs at once                                                           |

When you're at the limit, new runs **wait in a queue** and start as others finish. They don't fail.

To change your organization's limit, see [Organization settings](/zerve-docs/administration/organization-settings.md).

## Fleet

A single [Fleet](/zerve-docs/compute/fleet.md) can have up to 250 runs. You can also set a lower concurrency limit for a Fleet.

## Automatic retries

If the compute running a block fails partway through for reasons outside your code, Zerve retries the run automatically, up to 3 times.

## Agents

| Limit                       | Value                                                                                                          |
| --------------------------- | -------------------------------------------------------------------------------------------------------------- |
| **Agent run**               | 60 minutes                                                                                                     |
| **Evolve Mode credit cap**  | Default 50 credits per run. See [Credit caps](/zerve-docs/agents-in-the-workspace/evolve-mode/credit-caps.md). |
| **Superagent daily budget** | Default and maximum 25,000 credits. See [Budgets and credits](/zerve-docs/superagents/budgets-and-credits.md). |

For every limit in one place, see [Limits](/zerve-docs/reference/limits.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.zerve.ai/zerve-docs/compute/limits-and-concurrency.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.