OpenDiLoCo 1.1B

Closed weights Prime Intellect 1.1B parameters July 2024

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
Prime Intellect
Organisation type
Industry
Country
United States of America
Published
10 July 2024
Authors
Sami Jaghouar, Jack Min Ong, Johannes Hagemann

What it does

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

Domain
Language
Task
Language modeling/generation, 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
1.1B

"We adopt the same hyperparameters as TinyLlama (Zhang et al., 2024), employing a model with 1.1B parameters, a learning rate of 4e−4 and a batch size of 2048."

Training data
tokens

44000 steps "For the scaled-up 1.1B parameter experiment, we limit it to 44, 000 steps because of the 4× larger batch size. " batch size 2048 sequence length 1024 2048*1024*44000 = 92274688000

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
6.1 × 10²⁰ FLOP

6ND = 6 FLOP / token / parameter * 1.1*10^9 parameters * 92274688000 tokens [see dataset size notes] = 6.0901294e+20 FLOP 4 replicas of 8xH100 (figure 8) -> 32 H100 GPUs

How it was established
Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA H100 SXM5 80GB
Chips used
32
Power draw
44.2 kW

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
Training code
Open source

https://github.com/PrimeIntellect-ai/OpenDiLoCo Apache 2.0

How it is classified

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

Record confidence
Confident

Sources

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

Reference
OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training
Last updated
28 November 2025

What the numbers mean

About this model

OpenDiLoCo 1.1B was published by Prime Intellect, in United States of America, in July 2024. industry is the category the publisher falls under.

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

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

How it was trained

Producing it required around 6.1 × 10²⁰ FLOP of arithmetic, on NVIDIA H100 SXM5 80GB, which is a statement about the training budget rather than about inference.

Answers

OpenDiLoCo 1.1B — common questions

01

Who created OpenDiLoCo 1.1B?

OpenDiLoCo 1.1B was published by Prime Intellect, based in United States of America, categorised as industry.

02

When was OpenDiLoCo 1.1B released?

OpenDiLoCo 1.1B was published in July 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is OpenDiLoCo 1.1B used for?

OpenDiLoCo 1.1B works in Language, and is recorded as handling language modeling/generation, 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.

04

How much compute was used to train OpenDiLoCo 1.1B?

Around 6.1 × 10²⁰ FLOP, on NVIDIA H100 SXM5 80GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

05

What GPU do I need to run OpenDiLoCo 1.1B?

None. OpenDiLoCo 1.1B 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.

06

Is OpenDiLoCo 1.1B open source?

No. OpenDiLoCo 1.1B has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does OpenDiLoCo 1.1B have?

OpenDiLoCo 1.1B has 1.1B parameters. "We adopt the same hyperparameters as TinyLlama (Zhang et al., 2024), employing a model with 1.1B parameters, a learning rate of 4e−4 and a batch size of 2048.". 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.

Source

Original publication

Record last updated 28 November 2025

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.