Qwen-7B
Qwen-7B established a continuously expanding Chinese open-model family for developers.
FAMILY / ALIBABA CLOUD
Qwen
An open multilingual family spanning dense, MoE, and hybrid-reasoning models.
- First model
- 2023
- Models
- 11
- Latest
- Qwen3.8-Flash-Next
01 / LINEAGE MAP
Model lineage
predecessor derived from
02 / GENERATIONS
What changed
Qwen2-72B
Qwen2 combined permissive Apache 2.0 licensing with strong multilingual capability, widening deployment options.
Qwen3-235B-A22B
Qwen3 brought hybrid reasoning and efficient MoE together in an Apache 2.0 open-weight model.
Qwen3-Next-80B-A3B
An 80B-total, 3B-active architecture preview combining hybrid linear attention and ultra-sparse MoE.
Qwen3-Max
A trillion-plus-parameter Qwen3 flagship for coding, agents, and million-token professional work.
Qwen3.5-397B-A17B
The first Qwen3.5 flagship, extending the Qwen3-Next hybrid architecture into a native multimodal agent model.
Qwen3.6-35B-A3B
The efficient Qwen3.6 MoE tier, using 3B active parameters for multimodal, coding, and tool tasks.
Qwen3.6-27B
The 27B dense Qwen3.6 tier for local deployment and general multimodal agents.
Qwen3.8-Max
It was the first open-weight Qwen Max-class release, bringing flagship-scale deployment into the open model line.
Qwen3.8-27B
The 27B dense open Qwen3.8 model for local deployment, vision, coding, and tool use.
Qwen3.8-Flash-Next
It introduced QSA, Gated Residual, and N-gram memory to reduce compute while advancing long-context agents.