# Chema Garabito

> Chema Garabito is speridlabs founder; Iris-3B co-author. Iris-3B on Anchor Terminal, with grades, an about and public profiles.

- Canonical: https://www.anchorterminal.com/people/chema-garabito/
- Markdown: https://www.anchorterminal.com/people/chema-garabito/index.md (~850 tokens)
- Slim: https://www.anchorterminal.com/people/chema-garabito/index.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/people/chema-garabito/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-27

Speridlabs founder; Iris-3B co-author.

Chema Garabito works at Speridlabs, a spatial AI lab building foundation models for 3D understanding and generation. He is a named author of its Iris-3B pixel-space text-to-image model and its ENEAS segmentation model, both published in 2026.

- X: https://x.com/chema_garabito

## What Chema builds

- [Iris-3B](https://www.anchorterminal.com/tools/iris-3b.md), graded D, 51.3/100, in Image generation. Iris-3B is an Apache-2.0 open-weight text-to-image model from Speridlabs that generates pixels directly, with no VAE. The release adds a 4-step Turbo version and fine-tunes for monocular depth and 4x image restoration. Speridlabs founder; Iris-3B co-author, researched 2026-10-27.

## Works with

- [Guillermo Garabito](https://www.anchorterminal.com/people/guillermo-garabito/), Co-founder
- [Hanqiu Li Cai](https://www.anchorterminal.com/people/hanqiu-li-cai/), Iris-3B project lead and first author; research internship ending

## Questions

### Who is Chema Garabito?

Chema Garabito works at Speridlabs, a spatial AI lab building foundation models for 3D understanding and generation. He is a named author of its Iris-3B pixel-space text-to-image model and its ENEAS segmentation model, both published in 2026.

### What does Speridlabs make?

Anchor Terminal lists Iris-3B from Speridlabs. Iris-3B is an Apache-2.0 open-weight text-to-image model from Speridlabs that generates pixels directly, with no VAE. The release adds a 4-step Turbo version and fine-tunes for monocular depth and 4x image restoration.

### How are Chema's tools graded?

Iris-3B is graded D, 51.3 out of 100, on Anchor Terminal's benchmark, which scores every listing against the same checklist.

## Sources

- https://speridlabs.com/research/iris
- https://x.com/chema_garabito
- https://www.google.com/search?q=Speridlabs+Guillermo+Garabito+LinkedIn
- https://es.linkedin.com/in/guillermo-garabito-b6933546
- https://github.com/hanqiuli
- https://www.linkedin.com/posts/hanqiu-li-cai_a-life-update-as-i-wrap-up-my-research-internship-activity-7516925555754311680-nc9K
- https://es.linkedin.com/in/hanqiu-li-cai
- https://speridlabs.com/
- https://speridlabs.com
- https://x.com/speridlabs
- https://github.com/speridlabs/iris-3b/issues

These are the people building the tools we list, named for their public role in the company or project behind a listing, from public pages, with the date it was researched. They don't work for Anchor Terminal (our own team is on the about page, /about/#author). We show public roles, public profiles and what the listing pages show, nothing private. To correct something, send an about or a photo, or have a page removed, write to privacy@anchorterminal.com.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp