InternLM

Closed weights Shanghai AI Lab,SenseTime 104B parameters July 2023

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
Shanghai AI Lab,SenseTime
Organisation type
Academia,Industry
Country
China, Hong Kong
Published
6 July 2023

What it does

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

Domain
Language
Task
Language modeling

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
104B

"We present InternLM, a multilingual foundational language model with 104B parameters"

Training data
1,600,000,000,000 tokens

"InternLM is pre-trained on a large corpora with 1.6T tokens"

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
10 × 10²³ FLOP

6 * 104b * 1.6T = 9.984e23

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 A100 SXM4 80 GB
Compute cost
$1,505,257

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
Unreleased

Though they released 7b and 20b models (https://github.com/InternLM/InternLM/tree/main/model_cards) 100b model is not found

How it is classified

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

Foundation model
Yes
Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

(from Google-translated page) "In addition to using academic datasets to evaluate InternLM, we also use human examinations to assess its capabilities. InternLM can achieve good scores on examination benchmarks such as MMLU, AGIEval, C-Eval, and GAOKAO-bench that cover different languages and subjects, scoring higher than ChatGPT on multiple benchmarks"

Record confidence
Confident

Sources

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

Last updated
18 December 2025

What the numbers mean

What this model is

InternLM was published by Shanghai AI Lab,SenseTime, in China, in July 2023. academia,Industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Training it took roughly 10 × 10²³ FLOP of computation, on NVIDIA A100 SXM4 80 GB — a measure of what producing the model cost, not of how fast it answers.

Around 1,600,000,000,000 tokens went into training it.

Its inclusion criterion is sOTA improvement.

Answers

InternLM — common questions

01

Who created InternLM?

InternLM was published by Shanghai AI Lab,SenseTime, based in China, categorised as academia,Industry.

02

When was InternLM released?

InternLM was published in July 2023. 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 InternLM used for?

InternLM works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train InternLM?

Around 10 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB. 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 InternLM?

None. InternLM 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 InternLM open source?

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

07

How many parameters does InternLM have?

InternLM has 104B parameters. "We present InternLM, a multilingual foundational language model with 104B parameters". 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 18 December 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.