Qwen(@Alibaba_Qwen)

Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next r...

Qwen (@Alibaba_Qwen) — Wed, 14 Oct 2026 03:43:40 GMT

Congrats to @lightseekorg on the impressive TokenSpeed results! 🚀 Great to see Qwen3.8-Flash-Next reaching 685 output tokens/s per user on Nvida GPUs. Excited to see the community unlock more of Qwen’s inference potential!

LightSeek Foundation@lightseekorg

685 output tokens/s per user on @Alibaba_Qwen Qwen3.8-Flash-Next.

Running TokenSpeed on 4× NVIDIA GB300 with NVFP4.

A look at the kernel and serving optimizations behind the results:

👉lightseek.org/blog/tokenspee…i

⭐github.com/lightseekorg/t…8

🔗 View Quoted Tweet

💬84🔄54❤️1007👀91642📊152

⚡ Powered by xgo.ing

QwenGyre addresses two challenges of XLong-horizon agentic RL.

Qwen (@Alibaba_Qwen) — Mon, 12 Oct 2026 13:11:38 GMT

QwenGyre addresses two challenges of XLong-horizon agentic RL.

💬9🔄5❤️144👀27728📊23

⚡ Powered by xgo.ing

Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It laun...

Qwen (@Alibaba_Qwen) — Mon, 12 Oct 2026 13:11:37 GMT

Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨

It launches with two core designs: 🥳
- Elastic Scheduler: reallocates GPUs between rollout & training as demand shifts—live executions never interrupted. Up to 1.85× speedup over Colocate, 1.78× over Async.
- Trajectory Processor: turns branching executions (compaction, sub-agents, retries) into prefix-shared trajectory trees with bounded, deduplicated training samples. Partial progress after timeout still gets scored.

Scaled to Qwen3.8-2.4T-A95B with ~700K tokens per rollout, QwenGyre lifts NL2RepoBench from 52.5% to 58.5% in 48 steps, cutting end-to-end training time by ~44% vs Async.

🔗 Read the paperarxiv.org/abs/2609.33848sk

💬147🔄309❤️3210👀233254📊693

⚡ Powered by xgo.ing

Edit:

Qwen (@Alibaba_Qwen) — Fri, 09 Oct 2026 13:24:10 GMT

Edit:

💬2🔄2❤️112👀26842📊14

⚡ Powered by xgo.ing

🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now av...

Qwen (@Alibaba_Qwen) — Fri, 09 Oct 2026 13:24:09 GMT

🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available!

Built on Qwen-Image-2.1, Turbo is an accelerated checkpoint on the same 7B visual generation architecture. 

Fewer steps does not mean lower quality: it still generates strong 2K images from text, and supports continued creation through natural-language edits, from adding accessories to changing a scene.

Start directly with Diffusers: load QwenImage21Pipeline and the checkpoint’s recommended 8-step sampling schedule is ready to go. 

🌐 Prefer an API? Qwen-Image-2.1 Pro and Turbo APIs are now officially live. Choose a hosted API for your application, or use the Turbo weights in your own workflow.

🤖 ModelScopmodelscope.cn/models/Qwen/Qw…1v8
🤗 Hugging Fahuggingface.co/Qwen/Qwen-Imag…eAmB
🔗 Pro modelstudio.console.alibabacloud.com/ap-southeast-1…7VCP7
🔗 Turbomodelstudio.console.alibabacloud.com/ap-southeast-1…TqiVZK

What will you create with 8 steps? Share your results with us!

Qwen@Alibaba_Qwen

Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨

A unified model for both generation and editing, delivering top-tier quality in a lightweight package.

Highlights: 👀
- Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs.
- Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images.
- Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products.
- Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography.

Start to create your next masterpiece with Qwen-Image-2.1! 🖼️

- Bloqwen.ai/blog?id=qwen-i…7jy
- GitHugithub.com/QwenLM/Qwen-Im…rWr
- Model Scopmodelscope.cn/models/Qwen/Qw…YFR
- Hugging Fachuggingface.co/Qwen/Qwen-Imag…bVS

🔗 View Quoted Tweet

💬210🔄534❤️5311👀731886📊1149

⚡ Powered by xgo.ing

Pics:

Qwen (@Alibaba_Qwen) — Fri, 09 Oct 2026 13:24:09 GMT

Pics:

💬14🔄6❤️196👀46961📊34

⚡ Powered by xgo.ing

Thanks for the support! @gmi_cloud

Qwen (@Alibaba_Qwen) — Fri, 09 Oct 2026 06:03:19 GMT

Thanks for the support! @gmi_cloud

💬4🔄0❤️38👀17957📊7

⚡ Powered by xgo.ing

A week of free access to Qwen3.8-Max, Qwen3.8-Flash, and Wan3.0 on @gmi_cloudis live. Explore what y...

Qwen (@Alibaba_Qwen) — Fri, 09 Oct 2026 03:36:58 GMT

A week of free access to Qwen3.8-Max, Qwen3.8-Flash, and Wan3.0 on @gmi_cloudis live. Explore what you can build with us now. 🙌

GMI Cloud@gmi_cloud

We're extending FREE Qwen 3.8 Max + Flash for 7 more days! 

And we've increased rate limits across all 3 models.

Built something with Qwen or Wan? Show us what you've got!

Tag us and @Alibaba_Qwen or @Alibaba_Wan. We'll pick 3 winners based on:
🏆 Most creative
🏆 Most challenging
🏆 Most effort put in

Each winner gets $200 cash + $200 in GMI credits!

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬70🔄68❤️1177👀134129📊213

⚡ Powered by xgo.ing

Qwen3.8-27B is now accessible via @nebiustf. Whether you are building agents or doing deep research,...

Qwen (@Alibaba_Qwen) — Wed, 30 Sep 2026 11:18:51 GMT

Qwen3.8-27B is now accessible via @nebiustf. Whether you are building agents or doing deep research, this 27B dense model is ready for your multi-step workflows! 🥳

Nebius Token Factory@nebiustf

Qwen3.8-27B is now live on Nebius Token Factory.

A compact 27B dense model for coding, research, and agent workflows, with a focus on planning and completing tasks across multiple steps.

Start building: tokenfactory.nebius.com/endpoints?moda…

🔗 View Quoted Tweet

💬66🔄16❤️344👀69791📊74

⚡ Powered by xgo.ing

Benchmark suite:

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 11:50:58 GMT

Benchmark suite:

💬2🔄0❤️46👀15724📊7

⚡ Powered by xgo.ing

Performance of Mobile Creative Agent:

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 11:50:57 GMT

Performance of Mobile Creative Agent:

💬1🔄1❤️46👀15887📊5

⚡ Powered by xgo.ing

Performance of Mobile Planner Agent:

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 11:50:56 GMT

Performance of Mobile Planner Agent:

💬7🔄1❤️93👀39752📊16

⚡ Powered by xgo.ing

Introducing Qwen Intelligence, bringing personal intelligence within everyone's reach. 📱✨ It launc...

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 11:50:54 GMT

Introducing Qwen Intelligence, bringing personal intelligence within everyone's reach. 📱✨

It launches with three SOTA agents: 🥳
- Mobile Planner Agent: plans, decomposes & orchestrates complex tasks. #1 on MobilePA-Bench, MobilePA-Bench Business & Memory.
- Mobile-Use Agent: gets things done, API-first with GUI fallback. MobileWorld 82.1, MobileWorld-Real 92.2, AndroidDaily 97.2, 90% end-to-end success rate.
- Mobile Creative Agent: turns one sentence into ready-to-use creations. Image generated in 3s, about 2x faster than leading peers.

We're also opening up our benchmark suite: MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety, covering planning, cross-app execution, real-device performance and safety.

🔗 Learn more about the agents:
- Qwen Intelligence official websitqwenintelligence.comJIL
- Mobile Planner Agengithub.com/Tongyi-MAI/Qwe…00x
- Mobile-Use Agentongyi-mai.github.io/Qwen-UI-Agent/agJ
- Mobile Creative Agenarxiv.org/abs/2608.16887IqV

🔗 Explore our open benchmark suite:
- MobilePA-Bentongyi-mai.github.io/MobilePA-Bench/0Ygp
- MobileWorld (GitHugithub.com/Tongyi-MAI/Mob…uCSJ
- Leaderboatongyi-mai.github.io/MobileWorld/#l…mJ6H

💬149🔄303❤️2956👀247658📊664

⚡ Powered by xgo.ing

⚡ Meet Qwen-Audio-3.1! ASR, TTS & Realtime are fully upgraded, joined by two new models: TTS-Next fo...

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 09:11:23 GMT

⚡ Meet Qwen-Audio-3.1! ASR, TTS & Realtime are fully upgraded, joined by two new models: TTS-Next for audio creation and ASR-Next for audio understanding.

Five models, one complete audio stack: understanding, generation, interaction & creation. 

Plus big price cuts across the lineup: TTS ~70% off, Realtime ~85% off, and ASR up to 95% off.

Highlights: 🥳
- ASR: stronger multilingual & dialect recognition, plus native polishing that auto-removes fillers & repetitions for cleaner, more logical transcripts.
- ASR-Next: supports multi-speaker ASR with speaker labels, timestamps & aligned transcripts, and understands emotions, ambient & machine sounds for sound captioning, event localization, audio QA & reasoning.
- TTS: multilingual & dialect synthesis with natural cross-lingual voice transfer; control emotion, speed & style via simple instructions.
- TTS-Next: unified LM + diffusion framework generating voice, sound effects & background audio in one pass for audiobooks, podcasts, games & ads. 
- Realtime: speak & listen at once with anytime interruption, just like a real call; it even slows down and responds empathetically when it senses a low mood.

Unlock the full potential of Qwen-Audio-3.1! 👇
- Blog…shanghai.oss-cn-shanghai.aliyuncs.com/cuijiayan.cjy/…Kg
- Qwen-Audio-3.1-ASRqwencloud.com/models/qwen-au…yz
- Qwen-Audio-3.1-Realtimeqwencloud.com/models/qwen-au…AC
- More APIs: coming soon @qwen_cloud

💬138🔄357❤️4042👀280151📊942

⚡ Powered by xgo.ing

Thanks @arena for the recognition! 🏆 Qwen-Image-2.1 is now the #1 open-source model in both the Ima...

Qwen (@Alibaba_Qwen) — Wed, 23 Sep 2026 01:24:44 GMT

Thanks @arena for the recognition! 🏆 Qwen-Image-2.1 is now the #1 open-source model in both the Image Edit and Text-to-Image Arenas. Try it now and show us what you create! 🎨

Arena.ai@arena

Qwen-Image-2.1 by @Alibaba_Qwen just landed as the #1 open source model in the Image Edit Arena and Text-to-Image Arena!

With 1367 pts in the Image Edit Arena, Qwen-Image-2.1 took the #1 spot among open. It landed #16 overall, just 3 pts from GPT-Image-1.5-high-fidelity at #15.

See the leaderboard for the Text-to-Image arena below.

Congrats to the @Alibaba_Qwen team on this contribution to the open source ecosystem!

🔗 View Quoted Tweet

💬33🔄27❤️551👀62985📊70

⚡ Powered by xgo.ing

Day-0 OpenVINO support from @inteldevs! 🥳 Qwen-Image-2.1 is ready to run optimized on Intel hardwar...

Qwen (@Alibaba_Qwen) — Tue, 22 Sep 2026 04:08:20 GMT

Day-0 OpenVINO support from @inteldevs! 🥳 Qwen-Image-2.1 is ready to run optimized on Intel hardware. One open-weight checkpoint for both generation and editing. 👇

Intel Devs@inteldevs

We're excited to offer Day0 OpenVINO support for Qwen-Image-2.1

Read more about what you can accomplish here: ms.spr.ly/6019a5nm5

🔗 View Quoted Tweet

💬10🔄7❤️276👀53843📊30

⚡ Powered by xgo.ing

@ArchSenex Hi there, thanks for your question! 👋 Just a quick clarification: Outputs are not part o...

Qwen (@Alibaba_Qwen) — Mon, 21 Sep 2026 04:55:01 GMT

@ArchSenex Hi there, thanks for your question! 👋 Just a quick clarification: Outputs are not part of the licensed Materials. Users retain the rights to images and other content they generate using the model.

💬10🔄10❤️247👀339853📊40

⚡ Powered by xgo.ing

Thanks @sgl_project for the day-0 support! 🙌 SGLang-Diffusion now serves Qwen-Image-2.1: text-to-im...

Qwen (@Alibaba_Qwen) — Mon, 21 Sep 2026 02:50:43 GMT

Thanks @sgl_project for the day-0 support! 🙌 SGLang-Diffusion now serves Qwen-Image-2.1: text-to-image generation, multi-image editing, and transparent RGBA output. Try it out! 🎨

SGLang@sgl_project

Day-0 support for @Alibaba_Qwen’s Qwen-Image 2.1 is here in SGLang-Diffusion!

🖥️ Native precision on a single RTX 4090 24GB with CPU offload
- 1024×1024 generation in 18.7s and image editing in 21.7s with 22.7 GiB peak GPU memory during requests. - On an RTX PRO 6000 96GB: 8.0s generation and 9.6s editing.
🎨 Text-to-image, multi-image editing, and transparent RGBA output—all with one checkpoint.
⚡ Native inference with TP/SP, LoRA, and OpenAI-compatible APIs.

40 denoising steps, one image per request, warmed HTTP latency including PNG output. No quantization.

Cookbook and GPU-specific commands below 👇

🔗 View Quoted Tweet

💬28🔄11❤️309👀56871📊45

⚡ Powered by xgo.ing

Qwen-Image-2.1 × @HuggingApps: live demo on Spaces! 🖼 One single checkpoint for generation and edit...

Qwen (@Alibaba_Qwen) — Mon, 21 Sep 2026 02:50:40 GMT

Qwen-Image-2.1 × @HuggingApps: live demo on Spaces! 🖼 One single checkpoint for generation and editing. Try it in your browser, no setup needed. 👇

Hugging Apps@HuggingApps

Qwen Image 2.1 is here! 🖼️

A 7B params native image generation and editing model, with up to 10 image references

The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI 

▶️ on Spacehuggingface.co/spaces/hugging…6j

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬15🔄16❤️351👀57700📊48

⚡ Powered by xgo.ing

Qwen-Image-2.1 is now supported in ComfyUI! Try it now and share your creations! 🖼️

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:52:24 GMT

Qwen-Image-2.1 is now supported in ComfyUI! Try it now and share your creations! 🖼️

ComfyUI@ComfyUI

Qwen-Image-2.1 is now supported in ComfyUI!

Open weights. One 7B checkpoint that generates and edits.

→ Image generation at native 2K
→ Instruction editing from up to 10 reference images in a single pass
→ RGBA output, alpha included

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬46🔄82❤️1287👀113832📊170

⚡ Powered by xgo.ing

Thanks @vllm_project for the day-0 support! 🙌 Generate, edit, transparent output — one model, ready...

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:52:21 GMT

Thanks @vllm_project for the day-0 support! 🙌 Generate, edit, transparent output — one model, ready to serve. Details 👇

vLLM@vllm_project

Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉

Generate, edit, and create transparent images with one model: a 7.1B DiT paired with Qwen3-VL-8B.

Setup and supported combinations �recipes.vllm.ai/Qwen/Qwen-Imag…Rp

🔗 View Quoted Tweet

💬23🔄18❤️372👀52076📊47

⚡ Powered by xgo.ing

Qwen-Image-2.1 also improves visual quality over its predecessor, particularly in the aesthetics of ...

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:06:44 GMT

Qwen-Image-2.1 also improves visual quality over its predecessor, particularly in the aesthetics of text and portraits. Below are several examples of text rendering.

💬4🔄4❤️238👀46566📊33

⚡ Powered by xgo.ing

Qwen-Image-2.1 supports a variety of editing tasks while balancing performance across them. For exam...

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:06:43 GMT

Qwen-Image-2.1 supports a variety of editing tasks while balancing performance across them. For example, given a three-view character reference, the model generates a complete storyboard.

💬5🔄10❤️270👀134579📊50

⚡ Powered by xgo.ing

Qwen-Image-2.1 now supports transparent image generation natively, and naturally supports editing tr...

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:06:41 GMT

Qwen-Image-2.1 now supports transparent image generation natively, and naturally supports editing transparent images as well.

💬6🔄4❤️367👀49381📊42

⚡ Powered by xgo.ing

Performance:

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:06:40 GMT

Performance:

💬5🔄13❤️395👀80033📊52

⚡ Powered by xgo.ing

Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image s...

Qwen (@Alibaba_Qwen) — Sun, 20 Sep 2026 13:06:39 GMT

Meet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨

A unified model for both generation and editing, delivering top-tier quality in a lightweight package.

Highlights: 👀
- Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs.
- Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images.
- Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products.
- Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography.

Start to create your next masterpiece with Qwen-Image-2.1! 🖼️

- Bloqwen.ai/blog?id=qwen-i…7jy
- GitHugithub.com/QwenLM/Qwen-Im…rWr
- Model Scopmodelscope.cn/models/Qwen/Qw…YFR
- Hugging Fachuggingface.co/Qwen/Qwen-Imag…bVS

💬304🔄890❤️8329👀2534379📊2101

⚡ Powered by xgo.ing

A great example of practical AI solving real-world problems! Faster than ever. Thanks for building w...

Qwen (@Alibaba_Qwen) — Sat, 19 Sep 2026 08:55:43 GMT

A great example of practical AI solving real-world problems! Faster than ever. Thanks for building with Qwen. @cerebras Try it out for yourself! 🏠

Cerebras@cerebras

We built Money Agent, a personal finance assistant powered by @Alibaba_Qwen 3.8 27B on Cerebras. 

Now you can turn a home-buying question into a real-time conversation, then into a financial goal, faster.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬27🔄14❤️491👀74237📊67

⚡ Powered by xgo.ing

Cases and more details:

Qwen (@Alibaba_Qwen) — Sat, 19 Sep 2026 07:08:13 GMT

Cases and more details:

Your browser does not support the video tag.

🔗 View on Twitter

💬2🔄4❤️90👀21379📊14

⚡ Powered by xgo.ing

Performance:

Qwen (@Alibaba_Qwen) — Sat, 19 Sep 2026 07:08:12 GMT

Performance:

💬3🔄2❤️91👀19095📊13

⚡ Powered by xgo.ing

Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢 ...

Qwen (@Alibaba_Qwen) — Sat, 19 Sep 2026 07:08:11 GMT

Meet Qwen3.8-LiveTranslate, Qwen's next-generation real-time simultaneous interpretation model! 📢

Built on an Interleave architecture, it improves faithfulness, fluency, and conciseness while reducing average lagging (LAAL) from 2.8s to 2.3s across 60 languages.

New capabilities: 🙌
- Real-time speaker diarization — distinguishes speakers in multi-party speech and preserves each speaker's voice through more stable voice cloning.
- Synchronized bilingual display — source and translation on screen together.
- Long-context disambiguation — leverages conversation history to clarify names and terminology for consistent translations.

Let's try Qwen3.8-LiveTranslate! 🥳
- Bloqwen.ai/blog?id=qwen3.…gUE
- QwenClouqwencloud.com/models/qwen3.8…IWb

💬111🔄303❤️2735👀309617📊604

⚡ Powered by xgo.ing

Cases and more details:

Qwen (@Alibaba_Qwen) — Fri, 18 Sep 2026 03:16:20 GMT

Cases and more details:

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄6❤️144👀31050📊18

⚡ Powered by xgo.ing

Performance and price:

Qwen (@Alibaba_Qwen) — Fri, 18 Sep 2026 03:16:19 GMT

Performance and price:

💬4🔄5❤️182👀27766📊23

⚡ Powered by xgo.ing

🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native...

Qwen (@Alibaba_Qwen) — Fri, 18 Sep 2026 03:16:18 GMT

🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities!

Native audio-video understanding, reasoning, and tool use come together in one model: understand the content, plan the task, execute with tools, and deliver the result.

Highlights: 🥳
- Audio-video intelligence that gets things done: jointly reason over what's seen and heard, and orchestrate tools across long workflows to auto-edit vlogs, translate short videos, and turn movies into recaps.
- A major leap: approaching Gemini 3.8 Flash in audio-video capabilities; +19.5 points on average in agent performance across WildClawBench-MM & UniClawBench.
- 1M-token context with agentic perception: actively explore long videos and locate key moments with higher accuracy, using 51.8% fewer tokens than static understanding on OmniVideoBench.

Video input costs are reduced by about 89% compared with Qwen3.5-Omni-Plus, making long-form audio-video understanding and agentic workflows more affordable than ever.

To help you build apps around Omni, we're also open-sourcing Qwen-MM-Plugins and Qwen-Live Harness! 🛠️

We can't wait to see what you build with Qwen3.8-Omni-Flash! 👀

- Blqwen.ai/blog?id=qwen3.…kqYF
- Qwencloqwencloud.com/models/qwen3.8…LAnD
- Qwen Studchat.qwen.aiaVNZ
- Aalibabacloud.com/help/en/model-…5YUt
- Qwen-MM-Plugigithub.com/QwenLM/Qwen-MM…DP3d
- Qwen-Live Harness: coming sgithub.com/QwenLM/Qwen-Li…Ibdy

💬177🔄362❤️3612👀283239📊733

⚡ Powered by xgo.ing

Fast meets open. 🚀 Qwen3.8-27B is now running on @cerebras with rapid inference. Try it now!

Qwen (@Alibaba_Qwen) — Sat, 12 Sep 2026 07:35:03 GMT

Fast meets open. 🚀 Qwen3.8-27B is now running on @cerebras with rapid inference. Try it now!

💬75🔄60❤️1282👀206543📊217

⚡ Powered by xgo.ing

Come build with Qwen🫴🫴

Qwen (@Alibaba_Qwen) — Thu, 03 Sep 2026 16:44:11 GMT

Come build with Qwen🫴🫴

QwenCloud@qwen_cloud

Qwen is up. Come say hi😃qwencloud.comC

🔗 View Quoted Tweet

💬102🔄51❤️1568👀179175📊192

⚡ Powered by xgo.ing

Meet E-Commerce Bench, a new benchmark for long-horizon autonomous business operations. 🚀 Agents s...

Qwen (@Alibaba_Qwen) — Thu, 03 Sep 2026 11:37:24 GMT

Meet E-Commerce Bench, a new benchmark for long-horizon autonomous business operations. 🚀

Agents start with ¥100,000 to run online stores for 365 days, handling sourcing, negotiation, pricing, promotions, inventory and cash flow, in a market driven by real e-commerce data.

What's inside: 👀
- Real economics: 6886 products, 576 suppliers (152 fraudsters), 600-minute workdays, storage fees, returns and reputation.
- Long-horizon learning: almost no model learns to buy cheaper or improve its strategies over a full year of operation.
- Seven-axis evaluation: beyond year-end assets, we score six more dimensions, revealing that no single model dominates across the board.

Learn more about E-Commerce Bench: 👇
- Bloqwen.ai/blog?id=e-comm…wiV
- Papearxiv.org/abs/2608.30730FUn
- Projececbench.github.ioRin
- Codgithub.com/QwenLM/E-Comme…7zE

💬73🔄59❤️645👀78180📊172

⚡ Powered by xgo.ing

🏆 #1 overall on Code Arena, and top of the Pareto frontier at $5/MToken. Thanks! @arena Give Qwen3...

Qwen (@Alibaba_Qwen) — Wed, 02 Sep 2026 02:57:07 GMT

🏆 #1 overall on Code Arena, and top of the Pareto frontier at $5/MToken. Thanks! @arena 
Give Qwen3.8-Max-0902 a spin on QwenCloud.🥳

Arena.ai@arena

Qwen3.8-Max-0902 by @Alibaba_Qwen just debuted at #1 overall in Code Arena: WebDev with 1,691 pts, and became the highest-scoring model on the Pareto frontier at a blended $5/MToken!

On the updated frontier, Qwen3.8-Max-0902 sits above HY4 Preview (1,629 pts at $2.08/MToken) and Qwen3.8-Flash-Next (1,620 pts at $0.39/MToken).

With this release, three models at the top of the overall leaderboard have moved off the Pareto frontier despite remaining #2–#4 overall:
- Claude Opus 5 (Max): #2, 1,688 pts, $20/MToken
- Kimi K3 (Max): #3, 1,674 pts, $12/MToken
- Qwen3.8 (Max): #4, 1,669 pts, $5/MToken

Congrats to the @Alibaba_Qwen team on the release!

🔗 View Quoted Tweet

💬52🔄54❤️717👀77908📊101

⚡ Powered by xgo.ing

🏆 #1 on CodeArena: WebDev leaderboard. Qwen3.8-Max-0902 jumps from 1669 to 1691, setting a new rec...

Qwen (@Alibaba_Qwen) — Wed, 02 Sep 2026 02:31:48 GMT

🏆 #1 on CodeArena: WebDev leaderboard.

Qwen3.8-Max-0902 jumps from 1669 to 1691, setting a new record for agentic coding (WebDev) workflows, with standout strength in multistep reasoning, tool use, and full app generation.

Thanks for the recognition! @arena

Arena.ai@arena

Big news: Qwen3.8-Max-0902 by @Alibaba_Qwen just debuted at #1 overall in the Code Arena: WebDev with 1691 pts!

It scores 3 pts above Claude Opus 5 (Max), 17 pts above Kimi K3 (Max), and 22 pts above the previous Qwen3.8-Max.

Priced at a blended $5/MToken, Qwen3.8-Max-0902 also claims the highest-scoring position on the Pareto frontier! Stay tuned for a closer look at its Pareto positioning, and for Agent Arena scores coming soon.

Its strength carries across every Code Arena: WebDev category:
- #1 in Data & Analytics and Consumer Product
- #2 in Brand & Marketing, Gaming, and Simulations
- #3 in Content Creation Tools and Reference-Based Design

Congrats to the @Alibaba_Qwen team on this huge update!

🔗 View Quoted Tweet

💬70🔄107❤️1239👀116969📊168

⚡ Powered by xgo.ing

🚀Qwen3.8-Max just got upgraded. Meet Qwen3.8-Max-0902! 2.4T parameters. 1M context tokens. Built f...

Qwen (@Alibaba_Qwen) — Wed, 02 Sep 2026 02:00:37 GMT

🚀Qwen3.8-Max just got upgraded. Meet Qwen3.8-Max-0902!

2.4T parameters. 1M context tokens. Built for real world complexity.

Further post trained on Coding & Cowork, Qwen3.8-Max-0902 now delivers stronger performance across complex enterprise tasks, scientific research, and long horizon workflows.

💰Pricing per 1M tokens:
$2 input, $6 output.
$0.17 explicit cache hit, $0.25 implicit cache hit.

Now live via API on QwenCloud. Come try it! 🙌
APqwencloud.com/models/qwen3.8…980

💬273🔄569❤️6018👀1189349📊1065

⚡ Powered by xgo.ing

CommerceAgentBench starts with real commercial demand, and Qwen3.8-Max delivers the strongest overal...

Qwen (@Alibaba_Qwen) — Tue, 01 Sep 2026 04:21:22 GMT

CommerceAgentBench starts with real commercial demand, and Qwen3.8-Max delivers the strongest overall performance among open-weight models. Let's test Qwen on your real-world workflows! 🔥

Accio@Accio_official

Most AI benchmarks test what a model says. In commerce, the hard part was never the answer. It’s execution.
We’ve open-sourced CommerceAgentBench: a benchmark for real commerce operations.
Early results are humbling. The best overall completion rate is ~62%.
Qwen @Alibaba_Qwen delivered the strongest overall performance across complex commercial workflows among the open-weight models evaluated.
Explore the benchmark and full results ↓
github.com/Accio-org/Comm…

🔗 View Quoted Tweet

💬29🔄23❤️335👀73380📊50

⚡ Powered by xgo.ing

125B/6B, 1M context, multimodal, now in OpenCode Go. ⚡ Happy coding with Qwen3.8-Flash!

Qwen (@Alibaba_Qwen) — Fri, 28 Aug 2026 06:41:07 GMT

125B/6B, 1M context, multimodal, now in OpenCode Go. ⚡ Happy coding with Qwen3.8-Flash!

OpenCode@opencode

Qwen3.8-Flash is now available in OpenCode Go

125B/6B · 1M context · multimodal

🔗 View Quoted Tweet

💬75🔄83❤️2095👀151377📊224

⚡ Powered by xgo.ing

Qwen3.8-Flash on @qwen_cloud: $0.15/1M input tokens, $0.47/1M output tokens, and just $0.016/1M on c...

Qwen (@Alibaba_Qwen) — Thu, 27 Aug 2026 06:49:33 GMT

Qwen3.8-Flash on @qwen_cloud: $0.15/1M input tokens, $0.47/1M output tokens, and just $0.016/1M on cache hits. ☁️ Come give it a try! 👇

QwenCloud@qwen_cloud

Qwen3.8-Flash API is live on QwenCloud. 262K native context, extensible to 1M, and priced to scale.

About Price⬇️
Input: $0.15 / 1M tokens
Output: $0.47 / 1M tokens
Cache hit: $0.016 / 1M tokens

Get your API key and start building：
qwencloud.com/models/qwen3.8…#QwenCloud#Qwen

🔗 View Quoted Tweet

💬41🔄12❤️262👀41422📊51

⚡ Powered by xgo.ing

Qwen3.8-Flash is now live on @OpenRouter! ⚡ Coding assistants, agentic workflows, long-video underst...

Qwen (@Alibaba_Qwen) — Thu, 27 Aug 2026 06:12:46 GMT

Qwen3.8-Flash is now live on @OpenRouter! ⚡ Coding assistants, agentic workflows, long-video understanding, all one API call away.

OpenRouter@OpenRouter

Qwen3.8 Flash from @Alibaba_Qwen is now live on OpenRouter.

A multimodal reasoning model for coding assistants, agentic workflows, visual understanding, codebase and document analysis, desktop interaction, charts, and long video.

openrouter.ai/qwen/qwen3.8-f…

🔗 View Quoted Tweet

💬31🔄26❤️459👀47495📊58

⚡ Powered by xgo.ing

Fantastic! 🥳 Thanks @lightseekorg for the TokenSpeed day-0 support. The new architecture is fully c...

Qwen (@Alibaba_Qwen) — Thu, 27 Aug 2026 03:35:16 GMT

Fantastic! 🥳 Thanks @lightseekorg for the TokenSpeed day-0 support. The new architecture is fully covered, from GDN + QSA to N-gram embedding with FP8.

LightSeek Foundation@lightseekorg

TokenSpeed Day 0 Support for @Alibaba_Qwen 3.8 Flash Next.

🔹GDN + Qwen Sparse Attention hybrid architecture
🔹Gated residual connections
🔹N-gram embedding

For N-gram embedding, TokenSpeed also supports FP8 precision.

As a preview for Qwen 4, we will continue optimizing beyond Day 0.

🔗 View Quoted Tweet

💬13🔄7❤️167👀34780📊23

⚡ Powered by xgo.ing

Thank you @NVIDIAAI for the day-0 support! 🙌 Developers can finetune the model for domain-specific...

Qwen (@Alibaba_Qwen) — Thu, 27 Aug 2026 03:00:36 GMT

Thank you @NVIDIAAI for the day-0 support! 🙌

Developers can finetune the model for domain-specific use cases using NVIDIA NeMo AutoModel:github.com/NVIDIA-NeMo/Au…j

NVIDIA AI@NVIDIAAI

Congrats to @Alibaba_Qwen on releasing Qwen3.8-Flash-Next, an experimental open-weight model that previews the Qwen4 architecture.

We’ve got Day 0 support to fine-tune with NVIDIA NeMo AutoModel and NeMo RL, plus recipes to run it with @sgl_project, @vllm_project and @lightseekorg TokenSpeed.

Get started: nvda.ws/4wV7yXp

🔗 View Quoted Tweet

💬27🔄26❤️718👀72453📊80

⚡ Powered by xgo.ing

A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 16:10:42 GMT

A high-performance 125B model now running locally on just 75GB RAM! Thank you @UnslothAI for the day-0 support.🥳

Unsloth AI@UnslothAI

Qwen3.8-Flash can now be run locally! 🔥

The 125B MoE model outperforms Claude-Opus-4.6 (Max).

Run on 75GB RAM via Unsloth GGUFs.

Qwen3.8-Flash-Next enables CPU RAM / unified mem setups to deliver near VRAM speeds.

Guide:unsloth.ai/docs/models/qw…L
GGUF:huggingface.co/unsloth/Qwen3.…j

🔗 View Quoted Tweet

💬65🔄96❤️1544👀114466📊208

⚡ Powered by xgo.ing

API is live on QwenCloud: https://t.co/nz3wibv0Lv 🙌Let's build something!

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 15:32:46 GMT

API is live on QwenCloud: qwencloud.com/models/qwen3.8…
🙌Let's build something!

Qwen@Alibaba_Qwen

⚡Meet Qwen3.8-Flash, a multimodal MoE and an early preview of the Qwen4 architecture, now open-weight!

The production version Qwen3.8-Flash will be available soon via QwenCloud API at just $ 0.16/1M input tokens and $ 0.47/1M output tokens.

125B parameters + 51B N-gram embeddings, with just 6B activated per token. Unmatched cost-efficiency.

What's new: 🥳
- Next architecture: GDN + QSA hybrid attention, Gated Residual, N-gram Embedding & Muon optimizer, serving as a precursor to the architecture used in Qwen4.
- Dramatically lower training and inference costs: trained at just 1/9 the cost of Qwen3.7-Plus, while outperforming it across the board with especially strong gains in coding and office tasks.
- Strong performance: scoring 58.7 on DeepSWE 1.1, 62.5 on SWE-bench Pro, 73.9 on CoWorkBench, 84.5 on AndroidWorld, and 95.7 on MathVision (with CI).
- 262K native context, extensible to 1M with YaRN.

We’re also releasing the weights for Qwen3.8-Flash-Next, giving the community an early look at the new architecture we’re exploring for Qwen4.🚀

We can't wait to see what you build with Qwen3.8-Flash!👀👇
- Blqwen.ai/blog?id=qwen3.…FLgJ
- Technical Repogithub.com/QwenLM/Qwen3.8…IkQO
- Hugging Fahuggingface.co/Qwen/Qwen3.8-F…AABt
- ModelScomodelscope.cn/models/Qwen/Qw…NuFG

🔗 View Quoted Tweet

💬22🔄14❤️259👀36543📊37

⚡ Powered by xgo.ing

Big thanks to @sgl_project for the day-0 support! 🙌 Qwen3.8-Flash-Next is ready to deploy with SGLa...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 13:48:52 GMT

Big thanks to @sgl_project for the day-0 support! 🙌 Qwen3.8-Flash-Next is ready to deploy with SGLang today.

SGLang@sgl_project

Congrats to @Alibaba_Qwen on launching Qwen3.8-Flash! SGLang is proud to be a day-0 partner supporting the new architecture preview for Qwen4.

It's a 125B main model with 51B of N-gram embeddings and 6B activated per token.

The 51B N-gram embeddings scale model capacity with almost no extra compute per token, and can sit in host memory with async prefetch instead of occupying GPU memory.

The GDN + QSA hybrid attention gives you efficient memory and precise retrieval at the same time on long-horizon tasks, while Gated Residual gives the model 4 lanes instead of 1 to pass information between layers. And it's trained with Muon!

We're excited for what's next with Qwen4, and we already have plenty of ideas for how to use the N-gram embeddings in new deployment setups. Stay tuned!

Blog and cookbook in the comments👇

🔗 View Quoted Tweet

💬11🔄6❤️224👀27637📊25

⚡ Powered by xgo.ing

Amazing! 🥳 Thanks @vllm_project for getting Qwen3.8-Flash-Next running on NVIDIA and AMD from day 0...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 13:17:23 GMT

Amazing! 🥳 Thanks @vllm_project for getting Qwen3.8-Flash-Next running on NVIDIA and AMD from day 0.

vLLM@vllm_project

Qwen3.8-Flash-Next from @Alibaba_Qwen has day-0 support in vLLM, verified on NVIDIA and AMD GPUs. 🎉

Ultra-sparse multimodal MoE: 125B params, 6B active, 262K native, 1M via YaRN. On top of those sits a separate 51B N-gram table you can offload.

Most of it will look familiar. The Gated DeltaNet layers reuse the KV path vLLM has had since Qwen3-Next: only a quarter of the layers hold a growing KV cache. Keep the 51B table in host RAM instead of HBM with VLLM_PLE_CPU_OFFLOAD=1. Qwen Sparse Attention is where the new engine work went. For now the model runs from vllm/vllm-openai:qwen38-flash-next.

Thanks to @Alibaba_Qwen for the weights, and for opening them this early! 🙌

recipes.vllm.ai/Qwen/Qwen3.8-F…rGA

🔗 View Quoted Tweet

💬24🔄21❤️569👀46619📊62

⚡ Powered by xgo.ing

Big thanks to @sgl_project for the day-0 support! 🙌 Qwen3.8-Flash-Next is ready to deploy with SGLa...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 13:11:12 GMT

Big thanks to @sgl_project for the day-0 support! 🙌 Qwen3.8-Flash-Next is ready to deploy with SGLang today.

SGLang@sgl_project

@Alibaba_Qwen Congrats on launching Qwen3.8-Flash! SGLang is proud to be a day-0 partner supporting the new architecture preview for Qwen4.

docs.sglang.io/cookbook/autor…

🔗 View Quoted Tweet

💬5🔄2❤️160👀12079📊15