TellWorldAI World Archive
Ask中文
News
Models
Organisations
People
Papers & concepts
Products & agents
Chips & robots
History
Topics
Ask中文

Home›Models

Model

Qwen3.8

Qwen3.8 is Alibaba's 2026 flagship line. Its open 2.4-trillion-parameter model, Qwen3.8-2.4T-A95B, released in August 2026, has 95B active parameters and a custom license.

Status AvailableModality Text, Image, VideoOpen weights YesContext (K tokens) 1000 Era Generative AI for everyone

Parameters
2.4T
License
Open weights
Access
API, App, Download
Release date
Developer
Alibaba Cloud

Background

Alibaba previewed Qwen3.8-Max, a 2.4-trillion-parameter model, in July 2026, and released the cloud version on 3 August 2026. Its predecessors in the proprietary line were Qwen3.7-Max, released in May 2026, and Qwen3.7-Plus, released in June 2026. [1]

Open weights

Open weights for Qwen3.8-2.4T-A95B were released on 12 August 2026. The model has 2.4 trillion total parameters, with 95 billion activated. [1][2]

The architecture has 92 layers that alternate Gated DeltaNet and Gated Attention blocks. Each block is followed by a mixture-of-experts layer with 512 experts, of which 10 routed and 1 shared expert are active. The design also uses multi-token prediction, which trains the model to predict several upcoming tokens. [2]

The open checkpoint is text-only and keeps thinking mode always on, meaning it always produces a reasoning phase before answering. The Qwen3.8-Max cloud model adds vision input, a non-thinking mode, a default context of one million tokens and built-in tools. [2]

License

The open weights carry a custom license rather than a standard open-source one. Wikipedia reports that providers with annual revenue above 50 million US dollars need a commercial license from Alibaba. [1][2]

Reported results

Alibaba reported these scores for Qwen3.8-Max: 86.6 on Terminal Bench 2.1, 67.7 on SWE-bench Pro, 92.6 on GPQA Diamond, and 43.6 on HLE, or 56.2 with tools. HLE is Humanity's Last Exam, a hard academic benchmark. [2]

Smaller and related models

Qwen3.8-27B followed on 14 August 2026 under Apache 2.0. It accepts image input and offers a non-thinking mode. [1]

Qwen3.8-Flash was released on 26 August 2026, with the Flash-Next weights under the Qwen Community 1.0 license. Qwen3.8-Omni-Flash followed on 18 September 2026. [1]

Context and position

The native context is 262,144 tokens, which can be extended to about one million. The line is the successor to Qwen3.6. In this release, the cloud version of Qwen3.8-Max came on 3 August, and the open weights followed on 12 August. For readers, the important distinctions are which version is open, which license applies, and which features are available only through the hosted model. [1][2]

CapabilitiesLarge language modelsReasoning

TechniquesFoundation models

Ecosystem & regionOpen sourceChina

Version history

14
  1. 2023
    • Aug 3, 2023 Qwen (Tongyi Qianwen, 2023)

      Qwen, known in Chinese as Tongyi Qianwen (通义千问), is Alibaba's family of large language models. Its first open-weight model, Qwen-7B, was released on 3 August 2023, and the family has grown through many later versions.

  2. 2024
    • Feb 5, 2024 Qwen1.5

      Qwen1.5 is the Qwen family's open model release of February 2024, with base and chat models from 0.5B to 72B parameters, later extended to 110B, and a mixture-of-experts model.

    • Jun 7, 2024 Qwen2

      Qwen2 is the Qwen family's June 2024 generation, with five sizes from 0.5B to 72B parameters, context lengths up to 128K tokens, and most sizes released under Apache 2.0.

    • Sep 19, 2024 Qwen2.5

      Qwen2.5 is the Qwen family's September 2024 generation. Its launch included 13 open-weight models, with up to 18 trillion pretraining tokens, 128K context and most models under Apache 2.0.

    • Nov 28, 2024 QwQ-32B-Preview

      QwQ-32B-Preview is an experimental reasoning research model released by the Qwen team on 28 November 2024, with 32B parameters, a 32K-token context and open Apache 2.0 weights. It scored strongly on maths benchmarks but the team documented clear failure modes.

  3. 2025
    • Jan 28, 2025 Qwen2.5-Max

      Qwen2.5-Max is Alibaba's large mixture-of-experts model, announced in January 2025. It was offered through Qwen Chat and the Alibaba Cloud API, and its weights were not released.

    • Mar 6, 2025 QwQ-32B

      A 32-billion-parameter open-weight reasoning model released by the Qwen team on 6 March 2025, trained mainly through scaled reinforcement learning and reported to perform comparably to the much larger DeepSeek-R1.

    • Apr 29, 2025 Qwen3

      Qwen3 is a family of large language models from Alibaba, released on 29 April 2025 under Apache 2.0. Its main feature is hybrid thinking, which lets one model reason step by step or answer directly.

    • Jul 21, 2025 Qwen3-2507

      Qwen3-2507 is a staged 2025 refresh of the open-weight Qwen3 models that split thinking and non-thinking into separate checkpoints, raised native context to 262,144 tokens, and scored far above the original non-thinking mode on published benchmarks.

    • Sep 2025 Qwen3-Max

      Qwen3-Max is Alibaba's proprietary trillion-parameter language model, released in September 2025 and served through Alibaba's API. It is the Max-tier flagship that followed Qwen2.5-Max.

    • Sep 2025 Qwen3-Next

      Qwen3-Next is an open-weight model from Alibaba's Qwen team, released in September 2025 under Apache 2.0. It has 80B total parameters, only 3B active per token, and a hybrid attention design later used in Qwen3.5.

  4. 2026
    • Feb 16, 2026 Qwen3.5

      Qwen3.5 is a natively multimodal model family from Alibaba released in February 2026. Its open flagship, Qwen3.5-397B-A17B, has 397B total parameters and 17B active per token, under Apache 2.0.

    • Apr 2, 2026 Qwen3.6

      A generation of Alibaba's Qwen models released in April 2026, spanning proprietary Plus and Max versions aimed at agentic coding and open-weight models such as Qwen3.6-35B-A3B, a 35B-parameter mixture-of-experts with 3B active parameters.

    • Aug 3, 2026 Qwen3.8 · This page

      Qwen3.8 is Alibaba's 2026 flagship line. Its open 2.4-trillion-parameter model, Qwen3.8-2.4T-A95B, released in August 2026, has 95B active parameters and a custom license.

20261

  1. ReleaseAlibaba releases Qwen3.8-Max, a 2.4-trillion-parameter model

    Alibaba released Qwen3.8-Max, a 2.4-trillion-parameter model, as a cloud service on 3 August 2026, and published open weights for a variant of it on 12 August 2026.

Developed by1

Alibaba Cloud

Successor of1

Qwen3.6

Powers1

Qwen app (Tongyi)

Uses2

Chain of thought and reasoning modelsMixture of experts (MoE)

Notes and sources

  1. Qwenhttps://en.wikipedia.org/wiki/Qwen
  2. Qwen/Qwen3.8-2.4T-A95Bhttps://huggingface.co/Qwen/Qwen3.8-2.4T-A95B
  3. Qwen organization pagehttps://huggingface.co/Qwen

Cite this page: Qwen3.8. TellWorld, https://www.tellworld.net/models/qwen3-8. Updated 2026-11-08