Modal logo
IntroductionCustom container images Custom container imagesPrivate registriesGPUs and other resources GPU accelerationReserving CPU and memoryScaling out Scaling outDicts and queuesConcurrent inputs (beta)Secrets and environment variables SecretsEnvironment variablesDeployment Managing deploymentsInvoke deployed functionsContinuous deploymentScheduling and cron jobsWeb endpoints Web endpointsStreaming web endpointsWeb endpoint URLsRequest timeoutsNetwork tunnelsData sharing and storage Passing local dataNetwork file systemsVolumesDynamic sandboxesReliability and robustness Failures and retriesPreemptionTimeoutsTroubleshootingSecurityOther topics File and project structureDeveloping and debuggingCold start performanceCheckpointingWorkspacesEnvironmentsJupyter notebooksAsynchronous usageGlobal variablesContainer lifecycle and parametersApps, stubs, and entrypoints

Reserving CPU and memory

Modal jobs are reserved 128 MiB of memory and 0.1 CPU cores by default. However, if there is free memory or CPU capacity on a worker, containers are free to spike above these limits.

CPU cores

If you have code that you want to run on a larger number of cores, you can request that using the cpu argument. This allows you to specify a floating-point number of CPU cores:

import modal

stub = modal.Stub()

@stub.function(cpu=8.0)
def my_function():
    # code here will have access to at least 8.0 cores
    ...

Memory

If you have code that needs more guaranteed memory, you can request it using the memory argument. This expects an integer number of megabytes:

import modal

stub = modal.Stub()

@stub.function(memory=32768)
def my_function():
    # code here will have access to at least 32 GiB of RAM
    ...

How much can I request?

For both CPU and memory, a maximum is enforced at function creation time to ensure your application can be scheduled for execution. Requests exceeding the maximum will be rejected with an InvalidError.

As the platform grows, we plan to support larger CPU and memory reservations.

Resource limits

We currently don’t support setting a hard limit on the resource usage of a function. But we do plan to add this feature so that users have more control over the resource consumption of their Modal applications.