TML-Interaction-Small

Closed weights Thinking Machines 276B parameters May 2026

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Thinking Machines
Organisation type
Industry
Country
United States of America
Published
11 May 2026

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language, Multimodal, Audio, Video
Task
Language modeling/generation, Chat, Question answering

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
276B

"The current TML-Interaction-Small is a 276B parameter MoE with 12B active."

Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Discretionary

Release from a commercially significant lab (e.g. >10B valuation)

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Interaction Models: A Scalable Approach to Human-AI Collaboration
Last updated
1 June 2026

What the numbers mean

Background

TML-Interaction-Small was published by Thinking Machines, in United States of America, in May 2026. industry is the category the publisher falls under.

It works in Language, Multimodal, Audio, Video, and is recorded as doing language modeling/generation, Chat, Question answering.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The reason it appears in this catalogue at all is discretionary.

Answers

TML-Interaction-Small — common questions

01

When was TML-Interaction-Small released?

TML-Interaction-Small was published in May 2026.

02

What is TML-Interaction-Small used for?

TML-Interaction-Small works in Language, Multimodal, Audio, Video, and is recorded as handling language modeling/generation, Chat, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

03

What GPU do I need to run TML-Interaction-Small?

None. TML-Interaction-Small is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

04

Is TML-Interaction-Small open source?

No. TML-Interaction-Small has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does TML-Interaction-Small have?

TML-Interaction-Small has 276B parameters. "The current TML-Interaction-Small is a 276B parameter MoE with 12B active.". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

06

Who created TML-Interaction-Small?

TML-Interaction-Small was published by Thinking Machines, based in United States of America, categorised as industry.

Source

Original publication

Record last updated 1 June 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.