Skip to content
Complexity-ML logo

Complexity-ML

Routes each token to two fixed experts through a precomputed token-ID table instead of a learned router, in compact transformer language models.

Actively maintained

Open sourceFor developers
complexity-ai.fr ↗GitHubLaunched on Product Hunt · Jul 23, 2026
Open complexity-ai.frAlternativesSet it up for my team
Complexity-ML: data, price, alternatives
  • Is it safe? We have not read the data policy of Complexity-ML yet. Read it on the official site before you upload anything.complexity-ai.fr ↗
  • Is it free? We have not read the prices of Complexity-ML yet; they are next in our queue. Until then, the official site has them.complexity-ai.fr ↗
  • What else does this? We have not measured alternatives for this one yet. If you know one, add it below.See ↓
At a glancechecked Oct 31, 2026

not read yet

Use

For
Researchers and engineers who want to inspect and reproduce transformer architectures and their checkpoints.
Activity
Actively maintainedsite updated 8 weeks ago
How it runs
API
Used for
  • inspect deterministic token routing in transformer checkpoints
  • serve token-routed models through an OpenAI-compatible API
  • run a compact object detector on your own images
Worth knowingcomputed from what we read · each with its source
  • Launched on Product Hunt on Jul 23, 2026Product Hunt ↗

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Complexity-ML for?

Sign in to leave a note
Questions this page answers
  • What is Complexity-ML?

    Routes each token to two fixed experts through a precomputed token-ID table instead of a learned router, in compact transformer language models.

  • Who is Complexity-ML for?

    Researchers and engineers who want to inspect and reproduce transformer architectures and their checkpoints.

  • Do people use Complexity-ML?

    Emerging.

  • Is Complexity-ML still maintained?

    Actively maintained: site updated 8 weeks ago.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk