ONE MODEL, EVERY PLATFORM

`qwen3.6-27b` deprecation and shutdown dates on every platform

qwen3.6-27b is tracked on 5 providers and hosting routes. First to go: Thinking Machines shuts down Qwen3.6-27B on Oct 23, 2026.

Last updated Oct 23, 2026

Thinking Machines

qwen3.6-27b on Thinking Machines
Date	Model	Status	Replacement	Source
Oct 23, 2026	`Qwen3.6-27B`	Shuts downTodayDeadline moved from Sep 2, 2026 to Oct 23, 2026	`Qwen3.8-27B`	Notice ↗

STACKIT

qwen3.6-27b on STACKIT
Date	Model	Status	Replacement	Source
—	`Qwen/Qwen3.6-27B`	Deprecated · no removal date	`Qwen/Qwen3.8-27B`	Notice ↗

CoreWeave

qwen3.6-27b on CoreWeave
Date	Model	Status	Replacement	Source
Oct 5, 2026	`Qwen/Qwen3.6-27B`	Retired	`Qwen/Qwen3.8-27B`	Notice ↗

Together AITogether AI fine-tuning

qwen3.6-27b on Together AI
Date	Model	Status	Replacement	Source
—	`Qwen/Qwen3.6-27B`	No deprecation notice tracked	None published	Notice ↗

Impossibl

qwen3.6-27b on Impossibl
Date	Model	Status	Replacement	Source
—	`qwen/qwen3.6-27b`	No deprecation notice tracked	None published	Notice ↗

Every provider sets its own dates

A deadline on one platform says nothing about another: OpenAI, Azure, Amazon Bedrock, Google Vertex AI and model routers each retire their own copies on their own schedule. Snapshots of the same model (for example dated versions) are listed separately because each has its own date. Rows marked “No deprecation notice tracked” mean ModelClock has not seen a retirement notice for that route, not that one cannot exist.