qwen3-coder-next:cloud

Upstream reference: Qwen3-Coder-Next

Publisher: Qwen Team, Alibaba Cloud

Qwen describes this coding model as a hybrid-attention mixture of experts, intended for development agents and local development.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Total parameters
80 billion Source
Active parameters
3 billion Source
Native context
262,144 tokens Source
Generation mode
Non-thinking only Source
Upstream license label
Apache-2.0 Source

Publisher-described uses

  • Coding agents and IDE/CLI development workflows. Source

Reference limitations

  • A cloud suffix does not establish exact runtime identity, precision or availability. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

Links

Recorded references do not establish downloadable weights, licensing or current availability.

80B
parameters
FP8
quantization
qwen3next
architecture
262144
context
apache-2.0
license
2026-01-30
released

Where qwen3-coder-next:cloud comes from

Company / lab

Alibaba Cloud Qwen

See every model and family from this maker.

Model family

qwen3-coder-next

Other versions and sizes in this line.

completiontools

Named in 3 observation pages

Browse the Observatory

AI-generated & AI-scored. Every observation on this site is produced and judged by AI, and AI makes mistakes. Treat each result as a recorded observation under a declared protocol, as of its date. Method and marker legend