# Qwen3.5

Qwen3.5 · Ikke lenger på aktiv radar. Lansering eller navneendring er ikke bekreftet.

- Utvikler: Alibaba
- Id: qwen3.5
- Ifølge rapporter: 2026-04-01T20:00:00.000Z
- Observasjon: 2026-11-13T17:16:47.346Z
  - [dokumentasjonslenke](https://qwen.ai/blog?id=3fff0020-4a7e-423f-ab76-21fd828cdc0a)
- Status: Ifølge rapporter
- Ikke lenger på aktiv radar. Lansering eller navneendring er ikke bekreftet.
- Kanonisk: https://alexgetman.com/nb/models/alibaba/qwen3-5/

## Spørsmål

### Når ble Qwen3.5 lansert?

Lanseringsdatoen er ikke fastslått. Signal Forge registrerte modellen første gang 2026-11-13.

## Tidslinje

- 2026-11-13T17:16:47.346Z · [Qwen · official article bodies](https://qwen.ai/blog?id=3fff0020-4a7e-423f-ab76-21fd828cdc0a)
- 2026-11-13T17:16:47.346Z · [Qwen · official article bodies](https://qwen.ai/blog?id=895af3b2-4bfb-4187-98b6-e4b11eb4c209)
> We are deeply grateful for the invaluable feedback from the Qwen3.5 era and eagerly anticipate the groundbreaking projects you will create with Qwen3.6-Plus
- 2026-11-13T18:38:52.337Z · [GitHub search · Alibaba · commits · bradleydavid09/bra · @bradleydavid09](https://github.com/bradleydavid09/bra/commit/43568ab226b1abb1efc44f7cf474ae826e054e62)
> 本文深度解析Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled这一结构化推理AI模型，涵盖其基于Qwen3.5混合专家架构、Claude-4.6 Opus推理轨迹蒸馏技术、355亿参数规模与LoRA微调策略；重点介绍链式推理能力、262K上下文支持、多语言适配及量化/分片等内存优化方法，并说明其在数学求解、代码生成、复杂逻辑分析等场景的应用优势与硬件要求。
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · Brontir/NInferno · @MichaelDementii](https://github.com/Brontir/NInferno/pull/898)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · CodyChuGit/ShotoPhopEX · @CodyChuGit](https://github.com/CodyChuGit/ShotoPhopEX/pull/113)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · Drazzct/Zalo-ai · @Drazzct](https://github.com/Drazzct/Zalo-ai/pull/1)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · GiggleLootCoin/RedAI · @GiggleLootCoin](https://github.com/GiggleLootCoin/RedAI/pull/5)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/11)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · PrimeIntellect-ai/prime-rl · @vikhyat](https://github.com/PrimeIntellect-ai/prime-rl/pull/4399)
> Loading an official `-FP8` release of the Qwen3.5 family into the trainer silently produces a broken model. Observed on a LoRA RL run of `Qwen/Qwen3.8-27B-FP8`
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · SciSharp/LLamaSharp · @zsogitbe](https://github.com/SciSharp/LLamaSharp/pull/1431)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13568)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · ggml-org/llama.cpp · @ravi9](https://github.com/ggml-org/llama.cpp/pull/32172)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · gpv74yhpnf-stack/graves-world · @gpv74yhpnf-stack](https://github.com/gpv74yhpnf-stack/graves-world/pull/29)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1319)
> it: PR 1 of the stack, #1318 (the Qwen3.5 rotary fix), is merged. Adds `qwen3_8b`: `Qwen/Qwen3-8B` text chat, served through `mstar serve`, `/generate` and `/v1/chat/completions`.
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1321)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1325)
> mpt_last_rows` (`mstar/engine/resources/attn/base.py`) were written for the Qwen3.5 MTP head, which is
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · qualcomm/vllm-qaic · @sahil139](https://github.com/qualcomm/vllm-qaic/pull/240)
> [v0.30.0] Add Qwen3.5 GDN support with on-device Hexagon kernels
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6092)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6137)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · strands-labs/strands-decider · @sromoam](https://github.com/strands-labs/strands-decider/pull/125)
> --vision` does. The vision tower is the 2B Qwen3.5 base model's own, unchanged: the decider's adapter never touched it. The build converts it to an
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · vllm-project/vllm · @simon-veitner-redhat](https://github.com/vllm-project/vllm/pull/63114)
> `model_executor/models/qwen3_5.py` and runs with torch.compile, like the other Qwen3.5 derivatives on main (D3, colqwen3_5, minicpmv4_6). It does not use main's new eager Qwen3.5 model.
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · voltaire-toledo/Local-LM-Bench · @voltaire-toledo](https://github.com/voltaire-toledo/Local-LM-Bench/pull/1)
- 2026-11-13T19:07:08.264Z · [GitHub search · Alibaba · pulls · yeixio/toskar-core · @gopherstein](https://github.com/yeixio/toskar-core/pull/1176)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Brontir/NInferno · @MichaelDementii](https://github.com/Brontir/NInferno/commit/c460e0924ea40c8b9d0dcb147985a94beb50a3dd)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Drazzct/Zalo-ai · @Drazzct](https://github.com/Drazzct/Zalo-ai/commit/b1f51c54664406f3f6b9690ae78854b103ce32d7)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · NVIDIA-NeMo/Gym · @JeffPengCoder](https://github.com/NVIDIA-NeMo/Gym/commit/fb91374856a97b708631467f0291a85bdb536404)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Vishwa-Balasubramanian/DOKU · @gokulrece2311](https://github.com/Vishwa-Balasubramanian/DOKU/commit/18ef00259526197c57c8ee1cbba520a6b6e18b59)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · Vishwa-Balasubramanian/DOKU · @gokulrece2311](https://github.com/Vishwa-Balasubramanian/DOKU/commit/efb07a12d34a29b966ad5ff08b354138165096a5)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · gpv74yhpnf-stack/graves-world · @gpv74yhpnf-stack](https://github.com/gpv74yhpnf-stack/graves-world/commit/d176e64ff83b896b91ad40f446db0ccf86ac0b49)
- 2026-11-13T19:07:40.219Z · [GitHub search · Alibaba · commits · trymirai/uzu · @alex-at-mirai](https://github.com/trymirai/uzu/commit/aa1596f89314b383fd7c063452307902f1c8c9f6)
> - Model names read "Qwen3.5 2B Mirai M".

## Dokumentasjonslenker

- [GitHub search · Alibaba · commits · Brontir/NInferno · @MichaelDementii](https://github.com/Brontir/NInferno/commit/c460e0924ea40c8b9d0dcb147985a94beb50a3dd)
- [GitHub search · Alibaba · pulls · Brontir/NInferno · @MichaelDementii](https://github.com/Brontir/NInferno/pull/898)
- [GitHub search · Alibaba · pulls · CodyChuGit/ShotoPhopEX · @CodyChuGit](https://github.com/CodyChuGit/ShotoPhopEX/pull/113)
- [GitHub search · Alibaba · commits · Drazzct/Zalo-ai · @Drazzct](https://github.com/Drazzct/Zalo-ai/commit/b1f51c54664406f3f6b9690ae78854b103ce32d7)
- [GitHub search · Alibaba · pulls · Drazzct/Zalo-ai · @Drazzct](https://github.com/Drazzct/Zalo-ai/pull/1)
- [GitHub search · Alibaba · pulls · GiggleLootCoin/RedAI · @GiggleLootCoin](https://github.com/GiggleLootCoin/RedAI/pull/5)
- [GitHub search · Alibaba · pulls · IBM/Evoflux · @renovate[bot]](https://github.com/IBM/Evoflux/pull/11)
- [GitHub search · Alibaba · commits · NVIDIA-NeMo/Gym · @JeffPengCoder](https://github.com/NVIDIA-NeMo/Gym/commit/fb91374856a97b708631467f0291a85bdb536404)
- [GitHub search · Alibaba · pulls · PrimeIntellect-ai/prime-rl · @vikhyat](https://github.com/PrimeIntellect-ai/prime-rl/pull/4399)
- [GitHub search · Alibaba · pulls · SciSharp/LLamaSharp · @zsogitbe](https://github.com/SciSharp/LLamaSharp/pull/1431)
- [GitHub search · Alibaba · commits · Vishwa-Balasubramanian/DOKU · @gokulrece2311](https://github.com/Vishwa-Balasubramanian/DOKU/commit/18ef00259526197c57c8ee1cbba520a6b6e18b59)
- [GitHub search · Alibaba · commits · Vishwa-Balasubramanian/DOKU · @gokulrece2311](https://github.com/Vishwa-Balasubramanian/DOKU/commit/efb07a12d34a29b966ad5ff08b354138165096a5)
- [GitHub search · Alibaba · pulls · anomalyco/models.dev · @models-dev-automation[bot]](https://github.com/anomalyco/models.dev/pull/13568)
- [GitHub search · Alibaba · commits · bradleydavid09/bra · @bradleydavid09](https://github.com/bradleydavid09/bra/commit/43568ab226b1abb1efc44f7cf474ae826e054e62)
- [GitHub search · Alibaba · pulls · ggml-org/llama.cpp · @ravi9](https://github.com/ggml-org/llama.cpp/pull/32172)
- [GitHub search · Alibaba · commits · gpv74yhpnf-stack/graves-world · @gpv74yhpnf-stack](https://github.com/gpv74yhpnf-stack/graves-world/commit/d176e64ff83b896b91ad40f446db0ccf86ac0b49)
- [GitHub search · Alibaba · pulls · gpv74yhpnf-stack/graves-world · @gpv74yhpnf-stack](https://github.com/gpv74yhpnf-stack/graves-world/pull/29)
- [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1319)
- [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1321)
- [GitHub search · Alibaba · pulls · mstar-project/mstar · @nick-rui](https://github.com/mstar-project/mstar/pull/1325)
- [GitHub search · Alibaba · pulls · qualcomm/vllm-qaic · @sahil139](https://github.com/qualcomm/vllm-qaic/pull/240)
- [GitHub search · Alibaba · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6092)
- [GitHub search · Alibaba · pulls · smg-project/smg · @hello-alexmcc](https://github.com/smg-project/smg/pull/6137)
- [GitHub search · Alibaba · pulls · strands-labs/strands-decider · @sromoam](https://github.com/strands-labs/strands-decider/pull/125)
- [GitHub search · Alibaba · commits · trymirai/uzu · @alex-at-mirai](https://github.com/trymirai/uzu/commit/aa1596f89314b383fd7c063452307902f1c8c9f6)
- [GitHub search · Alibaba · pulls · vllm-project/vllm · @simon-veitner-redhat](https://github.com/vllm-project/vllm/pull/63114)
- [GitHub search · Alibaba · pulls · voltaire-toledo/Local-LM-Bench · @voltaire-toledo](https://github.com/voltaire-toledo/Local-LM-Bench/pull/1)
- [GitHub search · Alibaba · pulls · yeixio/toskar-core · @gopherstein](https://github.com/yeixio/toskar-core/pull/1176)
- [qwen-articles](https://qwen.ai/blog?id=3fff0020-4a7e-423f-ab76-21fd828cdc0a)
- [qwen-articles](https://qwen.ai/blog?id=895af3b2-4bfb-4187-98b6-e4b11eb4c209)

## Signaler