Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Measure a served model with max benchmark v1.0.0

Use this resource to measure throughput, latency and GPU usage of a served MAX model

New

  • 588 downloads
  • 202 likes
  • 189 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-serving-benchmark

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent runs the max benchmark command against a running max serve endpoint, with a workload matched to the question. It then reads the throughput, latency and GPU metrics. You get figures to size a deployment.

Mostly picked by

Updated November 2, 2026

Card for the “Measure a served model with max benchmark” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: server check and choice of workload
  • references/flags.md: command and workload options
  • references/metrics.md: reading throughput and latency

Good fit for

  • You want tokens per second for a model before going to production
  • You size the number of GPUs for a request load

Not for

    Tags

    • benchmark
    • latency
    • throughput
    • gpu
    • server

    About

    You say

    “Measure the TTFT and throughput of my served model, with a concurrency ramp.”

    Card for the “Measure a served model with max benchmark” skill

    Skill published by modular under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to measure throughput, latency and GPU usage of a served MAX model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE15.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/flags.md6.5 KB
    • references/metrics.md4.5 KB
    • references/troubleshooting.md2.5 KB
    • SKILL.md8.2 KB

    Origin and licence

    Listed unmodified

    Author
    modular
    Source
    github.com/modular/skills/tree/9837a3af93e26456a6d05a9c05e8167cfb6e4f18/benchmark-model
    Licence
    Apache-2.0

    Notice

    « benchmark-model » (modular, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.