Qwen3-Max

Closed weights Alibaba 1T parameters September 2025

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
Alibaba
Organisation type
Industry
Country
China
Published
5 September 2025

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, Mathematical reasoning, Code generation, Quantitative reasoning, Retrieval-augmented generation, Translation

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
1T

MoE architecture

Training data
36,000,000,000,000 tokens

"was pretrained on 36 trillion 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
1.5 × 10²⁵ FLOP

6ND with: 36T tokens is taken from the qwen3 technical report 70B active params is based on it having >1T params, and the architectures of Qwen3-235B-A22B and Qwen3-Coder-480B-A35B

How it was established
Operation counting

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
API access
Training code
Unreleased

How it is classified

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

Likely above 10²³ FLOP
Yes
Why it is tracked
Discretionary
Record confidence
Speculative

Sources

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

Reference
Introducing Qwen3-Max-Preview (Instruct) — our biggest model yet, with over 1 trillion parameters!
Last updated
18 December 2025

What the numbers mean

What this model is

Qwen3-Max was published by Alibaba, in China, in September 2025. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Mathematical reasoning, Code generation, Quantitative reasoning, Retrieval-augmented generation, Translation.

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

Training and provenance

Training it took roughly 1.5 × 10²⁵ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Around 36,000,000,000,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: discretionary.

Answers

Qwen3-Max — common questions

01

Who created Qwen3-Max?

Qwen3-Max was published by Alibaba, based in China, categorised as industry.

02

When was Qwen3-Max released?

Qwen3-Max was published in September 2025.

03

What is Qwen3-Max used for?

Qwen3-Max works in Language, and is recorded as handling language modeling/generation, Question answering, Mathematical reasoning, Code generation, Quantitative reasoning, Retrieval-augmented generation, Translation. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train Qwen3-Max?

Around 1.5 × 10²⁵ FLOP. 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 Qwen3-Max?

None. Qwen3-Max 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 Qwen3-Max open source?

No. Qwen3-Max has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does Qwen3-Max have?

Qwen3-Max has 1T parameters. MoE architecture. 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.