[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.] #  @Alibaba_Qwen Qwen Qwen posts on X about ai, inference, endless, llamacpp the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXXX engagements in the last XX hours. ### Engagements: XXXXXXX [#](/creator/twitter::1753339277386342400/interactions)  - X Week XXXXXXX -XX% - X Month XXXXXXXXX -XX% - X Months XXXXXXXXXX +71% - X Year XXXXXXXXXX +1,321% ### Mentions: XX [#](/creator/twitter::1753339277386342400/posts_active)  - X Week XX +7.70% - X Month XX -XX% - X Months XXX +217% - X Year XXX +509% ### Followers: XXXXXXX [#](/creator/twitter::1753339277386342400/followers)  - X Week XXXXXXX +0.77% - X Month XXXXXXX +3.10% - X Months XXXXXXX +49% - X Year XXXXXXX +744% ### CreatorRank: XXXXXXX [#](/creator/twitter::1753339277386342400/influencer_rank)  ### Social Influence **Social category influence** [finance](/list/finance) XXXX% [technology brands](/list/technology-brands) XXXX% [travel destinations](/list/travel-destinations) XXXX% **Social topic influence** [ai](/topic/ai) #2630, [inference](/topic/inference) #82, [endless](/topic/endless) #791, [llamacpp](/topic/llamacpp) #5, [agentic](/topic/agentic) #60, [stem](/topic/stem) #1023, [gpu](/topic/gpu) #633, [to the](/topic/to-the) #2869, [level](/topic/level) #538, [searches](/topic/searches) XXXX% **Top accounts mentioned or mentioned by** [@grok](/creator/undefined) [@marcuscohenshit](/creator/undefined) [@cocktailpeanut](/creator/undefined) [@garciasusana](/creator/undefined) [@tradefollows_ai](/creator/undefined) [@krigetaa](/creator/undefined) [@arena](/creator/undefined) [@soholev](/creator/undefined) [@kllrbeez](/creator/undefined) [@canopywave_cw](/creator/undefined) [@rahulsutariya](/creator/undefined) [@kj_barbara](/creator/undefined) [@nbdpress](/creator/undefined) [@raktimmondol](/creator/undefined) [@_thomasip](/creator/undefined) [@linabdina](/creator/undefined) [@furkangozukara](/creator/undefined) [@alibabaqwen](/creator/undefined) [@aaroniker](/creator/undefined) [@nobanksnearby](/creator/undefined) ### Top Social Posts Top posts by engagements in the last XX hours "The Qwen Chat APP is now available for both iOS and Android users It's free to use and designed to assist with creativity collaboration and endless possibilities. Just ask and let Qwen Chat handle the rest. Scan the QR code to quickly access the Qwen Chat APP" [X Link](https://x.com/Alibaba_Qwen/status/1915761990703697925) 2025-04-25T13:37Z 126.9K followers, 231.5K engagements "🚀 Qwen Code v0.2.1 is here We shipped X versionsv0.1.0-v0.2.1 in just XX days with major improvements: What's New: 🌐 Free Web Search: Support for multiple providers. Qwen OAuth users get 2000 free searches per day 🎯 Smarter Code Editing: New fuzzy matching pipeline reduces errors and saves tokensfewer retries needed. ⚙More Control: Fine-tune AI behavior with temperature top_p and max tokens settings. 💻 Better IDE Integration: Enhanced Zed IDE support with todo and task management tools. 📝 Cleaner Output: Tool responses now use plain text instead of complex JSONeasier for AI to" [X Link](https://x.com/Alibaba_Qwen/status/1989368317011009901) 2025-11-14T16:22Z 126.9K followers, 197.9K engagements "🏆 We are incredibly honored to announce that our paper "Gated Attention for Large Language Models: Non-linearity Sparsity and Attention-Sink-Free" has received the NeurIPS 2025 Best Paper Award A huge congratulations to our dedicated research team for pushing the boundaries of AI. Read more:" [X Link](https://x.com/Alibaba_Qwen/status/1993854188171006453) 2025-11-27T01:27Z 126.9K followers, 462.6K engagements "🚀 Major Qwen Code v0.2.2-v0.3.0 update summary ✨ Two breakthrough features: 🎯 Stream JSON Support --output-format stream-json for streaming output --input-format stream-json for structured input 3-tier adapter architecture + complete session management Endless possibilities for SDK integration automation tools CI/CD pipelines 🌍 Full Internationalization Built-in EN/CN interface + custom language pack extensions /language ui zh-CN - One-click UI switching /language output Chinese - Set AI output language Global developers welcome to contribute your local language packs 🌏 🛡 Security &" [X Link](https://x.com/Alibaba_Qwen/status/1998234955210735668) 2025-12-09T03:35Z 126.9K followers, 70.8K engagements "🎙 Meet Qwen3-TTS-Flash the new text-to-speech model thats redefining voice AI Demo: Blog: Video: ✅ Best-in-class Chinese & English stability 🌍 SOTA multilingual WER for CN EN IT FR 🎭 XX expressive voices XX languages 🗣 Supports 9+ Chinese dialects: Cantonese Hokkien Sichuanese & more ⚡ Ultra-fast: First packet in just 97ms 🤖 Auto tone adaptation + robust text handling Perfect for apps games IVR content anywhere you need natural human-like speech" [X Link](https://x.com/Alibaba_Qwen/status/1970163551676592430) 2025-09-22T16:29Z 126.5K followers, 118.3K engagements "🚀Qwen3-VL-235B-A22B-Instruct is now #1 on OpenRouter for image processing XX% market share 🎉Huge thanks to our amazing community" [X Link](https://x.com/Alibaba_Qwen/status/1977566109198151692) 2025-10-13T02:44Z 126.4K followers, 146.6K engagements "🎨Qwen-Image-Edit-2509 just redefined architectural visualization 🏙From sketch to stunning reality seamlessly transfer ANY style onto buildings & cityscapes. Traditional Chinese patterns Done. Photorealistic urban render Perfect. AI doesnt just edit images it understands structure context and aesthetics. Thanks to community for sharing these inspiring case studies 🙏" [X Link](https://x.com/Alibaba_Qwen/status/1972558448626987264) 2025-09-29T07:05Z 126.7K followers, 64.6K engagements "Qwen Deep Research just got a major upgrade. ⚡ It now creates not only the report but also a live webpage 🌐 and a podcast 🎙 - Powered by Qwen3-Coder Qwen-Image and Qwen3-TTS. Your insights now visual and audible. ✨ 👉" [X Link](https://x.com/Alibaba_Qwen/status/1980609551486624237) 2025-10-21T12:18Z 126.8K followers, 204.1K engagements "Introducing Qwen3 We release and open-weight Qwen3 our latest large language models including X MoE models and X dense models ranging from 0.6B to 235B. Our flagship model Qwen3-235B-A22B achieves competitive results in benchmark evaluations of coding math general capabilities etc. when compared to other top-tier models such as DeepSeek-R1 o1 o3-mini Grok-3 and Gemini-2.5-Pro. Additionally the small MoE model Qwen3-30B-A3B outcompetes QwQ-32B with XX times of activated parameters and even a tiny model like Qwen3-4B can rival the performance of Qwen2.5-72B-Instruct. For more information feel" [X Link](https://x.com/Alibaba_Qwen/status/1916962087676612998) 2025-04-28T21:05Z 126.9K followers, 2.2M engagements "Qwen3-Coder is here ✅ Were releasing Qwen3-Coder-480B-A35B-Instruct our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves top-tier performance across multiple agentic coding benchmarks among open models including SWE-bench-Verified 🚀 Alongside the model we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code it includes custom prompts and function call protocols to fully unlock Qwen3-Coders capabilities." [X Link](https://x.com/Alibaba_Qwen/status/1947766835023335516) 2025-07-22T21:12Z 126.9K followers, 2.2M engagements "🚀 Excited to introduce Qwen-Image-Edit Built on 20B Qwen-Image it brings precise bilingual text editing (Chinese & English) while preserving style and supports both semantic and appearance-level editing. ✨ Key Features ✅ Accurate text editing with bilingual support ✅ High-level semantic editing (e.g. object rotation IP creation) ✅ Low-level appearance editing (e.g. addition/delete/insert) Try it now: Hugging Face: ModelScope: Blog: Github: API:" [X Link](https://x.com/Alibaba_Qwen/status/1957500569029079083) 2025-08-18T17:51Z 126.9K followers, 659.3K engagements "🚀 Introducing Qwen3-Next-80B-A3B the FUTURE of efficient LLMs is here 🔹 80B params but only 3B activated per token 10x cheaper training 10x faster inference than Qwen3-32B.(esp. @ 32K+ context) 🔹HybridArchitecture:GatedDeltaNet+GatedAttentionbestofspeed&recall 🔹 Ultra-sparse MoE: XXX experts XX routed + X shared 🔹 Multi-Token Prediction turbo-charged speculative decoding 🔹 Beats Qwen3-32B in perf rivals Qwen3-235B in reasoning & long-context 🧠 Qwen3-Next-80B-A3B-Instruct approaches our 235B flagship. 🧠 Qwen3-Next-80B-A3B-Thinking outperforms Gemini-2.5-Flash-Thinking. Try it now:" [X Link](https://x.com/Alibaba_Qwen/status/1966197643904000262) 2025-09-11T17:50Z 126.9K followers, 929.4K engagements "🚀 Introducing Qwen3-Omni the first natively end-to-end omni-modal AI unifying text image audio & video in one model no modality trade-offs 🏆 SOTA on 22/36 audio & AV benchmarks 🌍 119L text / 19L speech in / 10L speech out ⚡ 211ms latency 🎧 30-min audio understanding 🎨 Fully customizable via system prompts 🔗 Built-in tool calling 🎤 Open-source Captioner model (low-hallucination) 🌟 Whats Open-Sourced Weve open-sourced Qwen3-Omni-30B-A3B-Instruct Qwen3-Omni-30B-A3B-Thinking and Qwen3-Omni-30B-A3B-Captioner to empower developers to explore a variety of applications from" [X Link](https://x.com/Alibaba_Qwen/status/1970181599133344172) 2025-09-22T17:41Z 126.9K followers, 715.9K engagements "🔥 Qwen-Image-Edit-2509 IS LIVE and its a GAME CHANGER. 🔥 We didnt just upgrade it. We rebuilt it for creators designers and AI tinkerers who demand pixel-perfect control. ✅ Multi-Image Editing YES. Drag in person + product or person + scene it blends them like magic. No more Franken-images. ✅ Single-Image Rock-Solid Consistency. 👤 Faces stay you through poses filters and wild styles. 🛍 Products keep their identity ideal for ads & posters. ✍ Text Edit everything: content font color even material texture. ✅ ControlNet Built-In. Depth. Edges. Keypoints. Plug & play precision. ✨ Blog: 💬" [X Link](https://x.com/Alibaba_Qwen/status/1970189775467647266) 2025-09-22T18:13Z 126.9K followers, 338.6K engagements "🚀 We're thrilled to unveil Qwen3-VL the most powerful vision-language model in the Qwen series yet 🔥 The flagship model Qwen3-VL-235B-A22B is now open-sourced and available in both Instruct and Thinking versions: ✅ Instruct outperforms Gemini XXX Pro on key vision benchmarks ✅ Thinking achieves state-of-the-art (SOTA) performance on multimodal reasoning tasks ✨ Key breakthroughs: 🖥 Visual Agent: Operates GUIs on PC/phone understands buttons calls tools and completes real-world tasks (SOTA on OS World) 💻 Visual Coding: Transforms screenshots into code (HTML/CSS/JS true "what you see is" [X Link](https://x.com/Alibaba_Qwen/status/1970594923503391182) 2025-09-23T21:03Z 126.9K followers, 333K engagements "🚀 Qwen3-Max is hereno preview just power Qwen Blog: API: Weve supercharged coding & agentic skillsnow Qwen3-Max-Instruct without thinking rivaling top models on SWE-Bench Tau2-Bench SuperGPQA LiveCodeBench and AIME25. With Qwen3-Max-Thinking equipped with tool use and deployed in heavy mode its nearly perfect on key benchmarks. Built on massive scale + data and backed by relentless compute scaling in pre-training & RL. This is Qwens new flagship. Try it now 💡" [X Link](https://x.com/Alibaba_Qwen/status/1970599097297183035) 2025-09-23T21:20Z 126.9K followers, 731.2K engagements "🚀 Qwen3-VL-30B-A3B-Instruct & Thinking are here Smaller size same powerhouse performance 💪packed with all the capabilities of Qwen3-VL 🔧 With just 3B active params its rivaling GPT-5-Mini & Claude4-Sonnet and often beating them across STEM VQA OCR Video Agent tasks and more. And thats not all: were also releasing an FP8 version plus the FP8 of the massive Qwen3-VL-235B-A22B Try it out and make your multimodal AI applications run faster🧠🖼 QwenChat: Github&Cookbooks API: Blog ModelScope: HuggingFace:" [X Link](https://x.com/Alibaba_Qwen/status/1974289216113947039) 2025-10-04T01:43Z 126.9K followers, 328.2K engagements "IntroducingthecompactdenseversionsofQwen3-VLnowavailablein4Band8BpairseachwithbothInstructandThinkingvariants. ✅LowerVRAMusage ✅FullQwen3-VLcapabilitiesretained ✅Strongperformanceacrosstheboard DespitetheirsizetheyoutperformmodelslikeGemini2.5FlashLiteandGPT-5NanoandoftenbeatthemonbenchmarksspanningSTEMVQAOCRvideounderstandingagenttasksandmore.InmanycasestheyevenrivalourflagshipQwen2.5-VL-72Bfromjustsixmonthsago PlusFP8versionsarealsoavailableforefficientdeployment. Hugging Face: ModelScope: Qwen3-VL-8B-Instruct API Qwen3-VL-8B-Thinking API Cookbooks:" [X Link](https://x.com/Alibaba_Qwen/status/1978150959621734624) 2025-10-14T17:28Z 126.9K followers, 349.7K engagements "Introducing Qwen3-VL-2B and Qwen3-VL-32B From edge to cloud these dense powerhouses deliver ultimate performance per GPU memory packing the full capabilities of Qwen3-VL into compact and scalable forms. 🔥 Qwen3-VL-32B outperforms GPT-5 mini & Claude X Sonnet across STEM VQA OCR video understanding agent tasks and more. 💡 It matches models up to 235B (even beating them on OSWorld) with only 32B parameters. ⚡ FP8 versions available for ultra-efficient deployment. 🔧 Also releasing Instruct & Thinking variants for flexible use cases. Try it now: Hugging API - instruct: API - thinking: Cookbook:" [X Link](https://x.com/Alibaba_Qwen/status/1980665932625383868) 2025-10-21T16:02Z 126.9K followers, 270.3K engagements "🎉Qwen3-VLisnowavailableonllama.cpp Runthispowerfulvision-languagemodeldirectlyonyourpersonaldevicesfullysupportedonCPUCUDAMetalVulkanandotherbackends. WevealsoreleasedGGUFweightsforallvariantsfrom2Bupto235B.Downloadandenjoy🚀 🤗 Hugging Face: 🤖 ModelScope: 📌 PR:" [X Link](https://x.com/Alibaba_Qwen/status/1984634293004747252) 2025-11-01T14:51Z 126.9K followers, 241.5K engagements "Weve released an early preview of Qwen3-Max-Thinkingan intermediate checkpoint still in training. Even at this stage when augmented with tool use and scaled test-time compute it achieves XXX% on challenging reasoning benchmarks like AIME 2025 and HMMT. YoucantrythecurrentversioninQwenChat and Alibaba Cloud APImoretocomeastrainingcontinues. Qwen Chat: Alibaba Cloud API enable_thinking=True:" [X Link](https://x.com/Alibaba_Qwen/status/1985347830110970027) 2025-11-03T14:06Z 126.9K followers, 179.4K engagements "🚀 Huge shoutout to @arena for launching Arena Expert a game-changer for evaluating LLMs on real expert-level prompts across X critical domains. 🎯 Qwen3-max-preview ranked #4 globally 🎯 Qwen3-235B-A22B-Thinking-2507 ranked #1 among all open-source models Proud of what open-source AI can achieve and excited to keep pushing the frontier together. 💪" [X Link](https://x.com/Alibaba_Qwen/status/1986340017715941396) 2025-11-06T07:48Z 126.9K followers, 69.1K engagements "🚀 Qwen DeepResearch 2511 is LIVE 🚀 We've just dropped a major upgrade making your research deeper faster and smarter 🔗 APP: ✨ Dual Mode Selection: Normal Mode: Efficient & versatile for most needs Advanced Mode: Go deeper Devotes extra time for a more thorough analysis. 🧠 📄 File Uploads Enabled: Now you can easily upload your documents or images for the AI to analyze ⚡ Boosted Search Power: Drastically improved search efficiency & depth. Read and process more web info in less time 📊 Precise Report Control: Command the report formatword count paragraphs & content Get comprehensive" [X Link](https://x.com/Alibaba_Qwen/status/1989026687611461705) 2025-11-13T17:44Z 126.9K followers, 136.7K engagements "10000000 users creating with Qwen Chat and were just getting started. From here lets begin 🚀" [X Link](https://x.com/Alibaba_Qwen/status/1990322403994657091) 2025-11-17T07:33Z 126.9K followers, 158K engagements "🚀 Qwen3-VL Tech report is now out on arXiv From pretraining to post-training architecture to infra data to evaluation weve packed in the details for anyone building on vision-language models. 🔥 X models 1M downloads in just over a month 🏆 Qwen3-VL-8B leads with 2M+ downloads 📚 Built on the shoulders of Qwen2.5-VL (2800+ citations in XX months) Check out the paper for insights baselines and future directions. Lets keep pushing VLMs forward together" [X Link](https://x.com/Alibaba_Qwen/status/1993941138844287049) 2025-11-27T07:13Z 126.9K followers, 198.3K engagements "llama.cpp (PR #16095) just added support for Qwen3-Next Qwens new hybrid architecture You can now run Qwen3-Next locally with efficient CPU/GPU inference. 🚀 🔗 PR:" [X Link](https://x.com/Alibaba_Qwen/status/1995384945553060021) 2025-12-01T06:50Z 126.9K followers, 102.5K engagements "Cool FP8 RL runs on just 5GB VRAM" [X Link](https://x.com/Alibaba_Qwen/status/1996474298169802799) 2025-12-04T06:59Z 126.9K followers, 67.8K engagements "Such an awesome moment" [X Link](https://x.com/Alibaba_Qwen/status/1996946894157947270) 2025-12-05T14:16Z 126.9K followers, 28.9K engagements "Our new Qwen3-TTS (version 2025-11-27) is here 🚀 We've leveled up on what matters most: ✨ More Personalities: Over XX high-quality voices from cute and playful to wise and stern. Find your perfect match 🌍 Global Reach: Now speaks XX languages (zh en de it pt es ja ko fr ru) & authentic dialects (Minnan Wu Cantonese Sichuan Beijing Nanjing Tianjin Shaanxi) 🗣 Insanely Natural: The rhythm and speed adapt just like a real person. It's uncanny. 🎧 Try it now: 🎙 Qwen Chat: click Response Read aloud: 📝 Blog: 🔌 Realtime API: 🔌 Offline API: 🎧 Demo: 🎧 Demo:" [X Link](https://x.com/Alibaba_Qwen/status/1996947806138126547) 2025-12-05T14:20Z 126.9K followers, 179.7K engagements "🚀 We introduce Soft Adaptive Policy Optimization (SAPO) a smooth stable and highly effective RL method for training large language models. Why SAPO 🔹 Hard clipping is brittle gradients vanish or explode 🔹 MoE models amplify variance making training even more unstable SAPO replaces hard boundaries with a continuous temperaturecontrolled gate that: ✨ Smooth trustregion behavior no abrupt gradient drop ✨ Sequence-level coherence align sequencelevel behavior ✨ Token-level adaptivity preserves useful gradients & boosts sample efficiency ✨ Asymmetric temperatures significantly improved stability" [X Link](https://x.com/Alibaba_Qwen/status/1998300361514500554) 2025-12-09T07:55Z 126.9K followers, 88.7K engagements "🚀 Qwen3-Omni-Flash just got a massive upgrade (2025-12-01 version) What's improved: 🎙 Enhanced multi-turn video/audio understanding - conversations flow naturally ✨ Customize your AI's personality through system prompts (think roleplay scenarios) 🗣 Smarter language handling + rock-solid support: XXX text languages XX speech 😊 Voices indistinguishable from humans Try it now: 🎙 Qwen Chat: click the VoiceChat and VideoChat button (bottom-right): 📝 Blog: 🎧 Demo: 🎧 Demo: ⚡ Realtime API 📥 Offline API" [X Link](https://x.com/Alibaba_Qwen/status/1998776328586477672) 2025-12-10T15:26Z 126.9K followers, 118.7K engagements "🧠 Your Personal AI Learning Tutor Is Here 🎓Stop merely memorizing. In Qwen Learn Mode Qwen Chat turns information into understanding that actually sticks.Powered by our Qwen3-Max model and grounded in cognitive psychology it designs a learning path tailored to the way you think. ✅ Guides you through Socratic-style dialogue instead of just giving you answers ✅ Adapts to your current level like a tutor who always works in your optimal learning zone ✅ Builds mental scaffolds so you can handle complex logic without feeling overwhelmedUnlock your potential not just the answer key. 🧬 ✨Try it now:" [X Link](https://x.com/Alibaba_Qwen/status/1999098020710002730) 2025-12-11T12:44Z 126.9K followers, 9937 engagements "🧠 Your Personal AI Learning Tutor Is Here 🎓Stop merely memorizing. In Qwen Learn Mode Qwen Chat turns information into understanding that actually sticks.Powered by our Qwen3-Max model and grounded in cognitive psychology it designs a learning path tailored to the way you think. ✅ Guides you through Socratic-style dialogue instead of just giving you answers ✅ Adapts to your current level like a tutor who always works in your optimal learning zone ✅ Builds mental scaffolds so you can handle complex logic without feeling overwhelmed Unlock your potential not just the answer key. 🧬 ✨Try it" [X Link](https://x.com/Alibaba_Qwen/status/1999108786821411130) 2025-12-11T13:27Z 126.9K followers, 133.7K engagements
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@Alibaba_Qwen Qwen
Qwen posts on X about ai, inference, endless, llamacpp the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXXX engagements in the last XX hours.
Engagements: XXXXXXX #
- X Week XXXXXXX -XX%
- X Month XXXXXXXXX -XX%
- X Months XXXXXXXXXX +71%
- X Year XXXXXXXXXX +1,321%
Mentions: XX #
- X Week XX +7.70%
- X Month XX -XX%
- X Months XXX +217%
- X Year XXX +509%
Followers: XXXXXXX #
- X Week XXXXXXX +0.77%
- X Month XXXXXXX +3.10%
- X Months XXXXXXX +49%
- X Year XXXXXXX +744%
CreatorRank: XXXXXXX #
Social Influence
Social category influence finance XXXX% technology brands XXXX% travel destinations XXXX%
Social topic influence ai #2630, inference #82, endless #791, llamacpp #5, agentic #60, stem #1023, gpu #633, to the #2869, level #538, searches XXXX%
Top accounts mentioned or mentioned by @grok @marcuscohenshit @cocktailpeanut @garciasusana @tradefollows_ai @krigetaa @arena @soholev @kllrbeez @canopywave_cw @rahulsutariya @kj_barbara @nbdpress @raktimmondol @_thomasip @linabdina @furkangozukara @alibabaqwen @aaroniker @nobanksnearby
Top Social Posts
Top posts by engagements in the last XX hours
"The Qwen Chat APP is now available for both iOS and Android users It's free to use and designed to assist with creativity collaboration and endless possibilities. Just ask and let Qwen Chat handle the rest. Scan the QR code to quickly access the Qwen Chat APP"
X Link 2025-04-25T13:37Z 126.9K followers, 231.5K engagements
"🚀 Qwen Code v0.2.1 is here We shipped X versionsv0.1.0-v0.2.1 in just XX days with major improvements: What's New: 🌐 Free Web Search: Support for multiple providers. Qwen OAuth users get 2000 free searches per day 🎯 Smarter Code Editing: New fuzzy matching pipeline reduces errors and saves tokensfewer retries needed. ⚙More Control: Fine-tune AI behavior with temperature top_p and max tokens settings. 💻 Better IDE Integration: Enhanced Zed IDE support with todo and task management tools. 📝 Cleaner Output: Tool responses now use plain text instead of complex JSONeasier for AI to"
X Link 2025-11-14T16:22Z 126.9K followers, 197.9K engagements
"🏆 We are incredibly honored to announce that our paper "Gated Attention for Large Language Models: Non-linearity Sparsity and Attention-Sink-Free" has received the NeurIPS 2025 Best Paper Award A huge congratulations to our dedicated research team for pushing the boundaries of AI. Read more:"
X Link 2025-11-27T01:27Z 126.9K followers, 462.6K engagements
"🚀 Major Qwen Code v0.2.2-v0.3.0 update summary ✨ Two breakthrough features: 🎯 Stream JSON Support --output-format stream-json for streaming output --input-format stream-json for structured input 3-tier adapter architecture + complete session management Endless possibilities for SDK integration automation tools CI/CD pipelines 🌍 Full Internationalization Built-in EN/CN interface + custom language pack extensions /language ui zh-CN - One-click UI switching /language output Chinese - Set AI output language Global developers welcome to contribute your local language packs 🌏 🛡 Security &"
X Link 2025-12-09T03:35Z 126.9K followers, 70.8K engagements
"🎙 Meet Qwen3-TTS-Flash the new text-to-speech model thats redefining voice AI Demo: Blog: Video: ✅ Best-in-class Chinese & English stability 🌍 SOTA multilingual WER for CN EN IT FR 🎭 XX expressive voices XX languages 🗣 Supports 9+ Chinese dialects: Cantonese Hokkien Sichuanese & more ⚡ Ultra-fast: First packet in just 97ms 🤖 Auto tone adaptation + robust text handling Perfect for apps games IVR content anywhere you need natural human-like speech"
X Link 2025-09-22T16:29Z 126.5K followers, 118.3K engagements
"🚀Qwen3-VL-235B-A22B-Instruct is now #1 on OpenRouter for image processing XX% market share 🎉Huge thanks to our amazing community"
X Link 2025-10-13T02:44Z 126.4K followers, 146.6K engagements
"🎨Qwen-Image-Edit-2509 just redefined architectural visualization 🏙From sketch to stunning reality seamlessly transfer ANY style onto buildings & cityscapes. Traditional Chinese patterns Done. Photorealistic urban render Perfect. AI doesnt just edit images it understands structure context and aesthetics. Thanks to community for sharing these inspiring case studies 🙏"
X Link 2025-09-29T07:05Z 126.7K followers, 64.6K engagements
"Qwen Deep Research just got a major upgrade. ⚡ It now creates not only the report but also a live webpage 🌐 and a podcast 🎙 - Powered by Qwen3-Coder Qwen-Image and Qwen3-TTS. Your insights now visual and audible. ✨ 👉"
X Link 2025-10-21T12:18Z 126.8K followers, 204.1K engagements
"Introducing Qwen3 We release and open-weight Qwen3 our latest large language models including X MoE models and X dense models ranging from 0.6B to 235B. Our flagship model Qwen3-235B-A22B achieves competitive results in benchmark evaluations of coding math general capabilities etc. when compared to other top-tier models such as DeepSeek-R1 o1 o3-mini Grok-3 and Gemini-2.5-Pro. Additionally the small MoE model Qwen3-30B-A3B outcompetes QwQ-32B with XX times of activated parameters and even a tiny model like Qwen3-4B can rival the performance of Qwen2.5-72B-Instruct. For more information feel"
X Link 2025-04-28T21:05Z 126.9K followers, 2.2M engagements
"Qwen3-Coder is here ✅ Were releasing Qwen3-Coder-480B-A35B-Instruct our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves top-tier performance across multiple agentic coding benchmarks among open models including SWE-bench-Verified 🚀 Alongside the model we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code it includes custom prompts and function call protocols to fully unlock Qwen3-Coders capabilities."
X Link 2025-07-22T21:12Z 126.9K followers, 2.2M engagements
"🚀 Excited to introduce Qwen-Image-Edit Built on 20B Qwen-Image it brings precise bilingual text editing (Chinese & English) while preserving style and supports both semantic and appearance-level editing. ✨ Key Features ✅ Accurate text editing with bilingual support ✅ High-level semantic editing (e.g. object rotation IP creation) ✅ Low-level appearance editing (e.g. addition/delete/insert) Try it now: Hugging Face: ModelScope: Blog: Github: API:"
X Link 2025-08-18T17:51Z 126.9K followers, 659.3K engagements
"🚀 Introducing Qwen3-Next-80B-A3B the FUTURE of efficient LLMs is here 🔹 80B params but only 3B activated per token 10x cheaper training 10x faster inference than Qwen3-32B.(esp. @ 32K+ context) 🔹HybridArchitecture:GatedDeltaNet+GatedAttentionbestofspeed&recall 🔹 Ultra-sparse MoE: XXX experts XX routed + X shared 🔹 Multi-Token Prediction turbo-charged speculative decoding 🔹 Beats Qwen3-32B in perf rivals Qwen3-235B in reasoning & long-context 🧠 Qwen3-Next-80B-A3B-Instruct approaches our 235B flagship. 🧠 Qwen3-Next-80B-A3B-Thinking outperforms Gemini-2.5-Flash-Thinking. Try it now:"
X Link 2025-09-11T17:50Z 126.9K followers, 929.4K engagements
"🚀 Introducing Qwen3-Omni the first natively end-to-end omni-modal AI unifying text image audio & video in one model no modality trade-offs 🏆 SOTA on 22/36 audio & AV benchmarks 🌍 119L text / 19L speech in / 10L speech out ⚡ 211ms latency 🎧 30-min audio understanding 🎨 Fully customizable via system prompts 🔗 Built-in tool calling 🎤 Open-source Captioner model (low-hallucination) 🌟 Whats Open-Sourced Weve open-sourced Qwen3-Omni-30B-A3B-Instruct Qwen3-Omni-30B-A3B-Thinking and Qwen3-Omni-30B-A3B-Captioner to empower developers to explore a variety of applications from"
X Link 2025-09-22T17:41Z 126.9K followers, 715.9K engagements
"🔥 Qwen-Image-Edit-2509 IS LIVE and its a GAME CHANGER. 🔥 We didnt just upgrade it. We rebuilt it for creators designers and AI tinkerers who demand pixel-perfect control. ✅ Multi-Image Editing YES. Drag in person + product or person + scene it blends them like magic. No more Franken-images. ✅ Single-Image Rock-Solid Consistency. 👤 Faces stay you through poses filters and wild styles. 🛍 Products keep their identity ideal for ads & posters. ✍ Text Edit everything: content font color even material texture. ✅ ControlNet Built-In. Depth. Edges. Keypoints. Plug & play precision. ✨ Blog: 💬"
X Link 2025-09-22T18:13Z 126.9K followers, 338.6K engagements
"🚀 We're thrilled to unveil Qwen3-VL the most powerful vision-language model in the Qwen series yet 🔥 The flagship model Qwen3-VL-235B-A22B is now open-sourced and available in both Instruct and Thinking versions: ✅ Instruct outperforms Gemini XXX Pro on key vision benchmarks ✅ Thinking achieves state-of-the-art (SOTA) performance on multimodal reasoning tasks ✨ Key breakthroughs: 🖥 Visual Agent: Operates GUIs on PC/phone understands buttons calls tools and completes real-world tasks (SOTA on OS World) 💻 Visual Coding: Transforms screenshots into code (HTML/CSS/JS true "what you see is"
X Link 2025-09-23T21:03Z 126.9K followers, 333K engagements
"🚀 Qwen3-Max is hereno preview just power Qwen Blog: API: Weve supercharged coding & agentic skillsnow Qwen3-Max-Instruct without thinking rivaling top models on SWE-Bench Tau2-Bench SuperGPQA LiveCodeBench and AIME25. With Qwen3-Max-Thinking equipped with tool use and deployed in heavy mode its nearly perfect on key benchmarks. Built on massive scale + data and backed by relentless compute scaling in pre-training & RL. This is Qwens new flagship. Try it now 💡"
X Link 2025-09-23T21:20Z 126.9K followers, 731.2K engagements
"🚀 Qwen3-VL-30B-A3B-Instruct & Thinking are here Smaller size same powerhouse performance 💪packed with all the capabilities of Qwen3-VL 🔧 With just 3B active params its rivaling GPT-5-Mini & Claude4-Sonnet and often beating them across STEM VQA OCR Video Agent tasks and more. And thats not all: were also releasing an FP8 version plus the FP8 of the massive Qwen3-VL-235B-A22B Try it out and make your multimodal AI applications run faster🧠🖼 QwenChat: Github&Cookbooks API: Blog ModelScope: HuggingFace:"
X Link 2025-10-04T01:43Z 126.9K followers, 328.2K engagements
"IntroducingthecompactdenseversionsofQwen3-VLnowavailablein4Band8BpairseachwithbothInstructandThinkingvariants. ✅LowerVRAMusage ✅FullQwen3-VLcapabilitiesretained ✅Strongperformanceacrosstheboard DespitetheirsizetheyoutperformmodelslikeGemini2.5FlashLiteandGPT-5NanoandoftenbeatthemonbenchmarksspanningSTEMVQAOCRvideounderstandingagenttasksandmore.InmanycasestheyevenrivalourflagshipQwen2.5-VL-72Bfromjustsixmonthsago PlusFP8versionsarealsoavailableforefficientdeployment. Hugging Face: ModelScope: Qwen3-VL-8B-Instruct API Qwen3-VL-8B-Thinking API Cookbooks:"
X Link 2025-10-14T17:28Z 126.9K followers, 349.7K engagements
"Introducing Qwen3-VL-2B and Qwen3-VL-32B From edge to cloud these dense powerhouses deliver ultimate performance per GPU memory packing the full capabilities of Qwen3-VL into compact and scalable forms. 🔥 Qwen3-VL-32B outperforms GPT-5 mini & Claude X Sonnet across STEM VQA OCR video understanding agent tasks and more. 💡 It matches models up to 235B (even beating them on OSWorld) with only 32B parameters. ⚡ FP8 versions available for ultra-efficient deployment. 🔧 Also releasing Instruct & Thinking variants for flexible use cases. Try it now: Hugging API - instruct: API - thinking: Cookbook:"
X Link 2025-10-21T16:02Z 126.9K followers, 270.3K engagements
"🎉Qwen3-VLisnowavailableonllama.cpp Runthispowerfulvision-languagemodeldirectlyonyourpersonaldevicesfullysupportedonCPUCUDAMetalVulkanandotherbackends. WevealsoreleasedGGUFweightsforallvariantsfrom2Bupto235B.Downloadandenjoy🚀 🤗 Hugging Face: 🤖 ModelScope: 📌 PR:"
X Link 2025-11-01T14:51Z 126.9K followers, 241.5K engagements
"Weve released an early preview of Qwen3-Max-Thinkingan intermediate checkpoint still in training. Even at this stage when augmented with tool use and scaled test-time compute it achieves XXX% on challenging reasoning benchmarks like AIME 2025 and HMMT. YoucantrythecurrentversioninQwenChat and Alibaba Cloud APImoretocomeastrainingcontinues. Qwen Chat: Alibaba Cloud API enable_thinking=True:"
X Link 2025-11-03T14:06Z 126.9K followers, 179.4K engagements
"🚀 Huge shoutout to @arena for launching Arena Expert a game-changer for evaluating LLMs on real expert-level prompts across X critical domains. 🎯 Qwen3-max-preview ranked #4 globally 🎯 Qwen3-235B-A22B-Thinking-2507 ranked #1 among all open-source models Proud of what open-source AI can achieve and excited to keep pushing the frontier together. 💪"
X Link 2025-11-06T07:48Z 126.9K followers, 69.1K engagements
"🚀 Qwen DeepResearch 2511 is LIVE 🚀 We've just dropped a major upgrade making your research deeper faster and smarter 🔗 APP: ✨ Dual Mode Selection: Normal Mode: Efficient & versatile for most needs Advanced Mode: Go deeper Devotes extra time for a more thorough analysis. 🧠 📄 File Uploads Enabled: Now you can easily upload your documents or images for the AI to analyze ⚡ Boosted Search Power: Drastically improved search efficiency & depth. Read and process more web info in less time 📊 Precise Report Control: Command the report formatword count paragraphs & content Get comprehensive"
X Link 2025-11-13T17:44Z 126.9K followers, 136.7K engagements
"10000000 users creating with Qwen Chat and were just getting started. From here lets begin 🚀"
X Link 2025-11-17T07:33Z 126.9K followers, 158K engagements
"🚀 Qwen3-VL Tech report is now out on arXiv From pretraining to post-training architecture to infra data to evaluation weve packed in the details for anyone building on vision-language models. 🔥 X models 1M downloads in just over a month 🏆 Qwen3-VL-8B leads with 2M+ downloads 📚 Built on the shoulders of Qwen2.5-VL (2800+ citations in XX months) Check out the paper for insights baselines and future directions. Lets keep pushing VLMs forward together"
X Link 2025-11-27T07:13Z 126.9K followers, 198.3K engagements
"llama.cpp (PR #16095) just added support for Qwen3-Next Qwens new hybrid architecture You can now run Qwen3-Next locally with efficient CPU/GPU inference. 🚀 🔗 PR:"
X Link 2025-12-01T06:50Z 126.9K followers, 102.5K engagements
"Cool FP8 RL runs on just 5GB VRAM"
X Link 2025-12-04T06:59Z 126.9K followers, 67.8K engagements
"Such an awesome moment"
X Link 2025-12-05T14:16Z 126.9K followers, 28.9K engagements
"Our new Qwen3-TTS (version 2025-11-27) is here 🚀 We've leveled up on what matters most: ✨ More Personalities: Over XX high-quality voices from cute and playful to wise and stern. Find your perfect match 🌍 Global Reach: Now speaks XX languages (zh en de it pt es ja ko fr ru) & authentic dialects (Minnan Wu Cantonese Sichuan Beijing Nanjing Tianjin Shaanxi) 🗣 Insanely Natural: The rhythm and speed adapt just like a real person. It's uncanny. 🎧 Try it now: 🎙 Qwen Chat: click Response Read aloud: 📝 Blog: 🔌 Realtime API: 🔌 Offline API: 🎧 Demo: 🎧 Demo:"
X Link 2025-12-05T14:20Z 126.9K followers, 179.7K engagements
"🚀 We introduce Soft Adaptive Policy Optimization (SAPO) a smooth stable and highly effective RL method for training large language models. Why SAPO 🔹 Hard clipping is brittle gradients vanish or explode 🔹 MoE models amplify variance making training even more unstable SAPO replaces hard boundaries with a continuous temperaturecontrolled gate that: ✨ Smooth trustregion behavior no abrupt gradient drop ✨ Sequence-level coherence align sequencelevel behavior ✨ Token-level adaptivity preserves useful gradients & boosts sample efficiency ✨ Asymmetric temperatures significantly improved stability"
X Link 2025-12-09T07:55Z 126.9K followers, 88.7K engagements
"🚀 Qwen3-Omni-Flash just got a massive upgrade (2025-12-01 version) What's improved: 🎙 Enhanced multi-turn video/audio understanding - conversations flow naturally ✨ Customize your AI's personality through system prompts (think roleplay scenarios) 🗣 Smarter language handling + rock-solid support: XXX text languages XX speech 😊 Voices indistinguishable from humans Try it now: 🎙 Qwen Chat: click the VoiceChat and VideoChat button (bottom-right): 📝 Blog: 🎧 Demo: 🎧 Demo: ⚡ Realtime API 📥 Offline API"
X Link 2025-12-10T15:26Z 126.9K followers, 118.7K engagements
"🧠 Your Personal AI Learning Tutor Is Here 🎓Stop merely memorizing. In Qwen Learn Mode Qwen Chat turns information into understanding that actually sticks.Powered by our Qwen3-Max model and grounded in cognitive psychology it designs a learning path tailored to the way you think. ✅ Guides you through Socratic-style dialogue instead of just giving you answers ✅ Adapts to your current level like a tutor who always works in your optimal learning zone ✅ Builds mental scaffolds so you can handle complex logic without feeling overwhelmedUnlock your potential not just the answer key. 🧬 ✨Try it now:"
X Link 2025-12-11T12:44Z 126.9K followers, 9937 engagements
"🧠 Your Personal AI Learning Tutor Is Here 🎓Stop merely memorizing. In Qwen Learn Mode Qwen Chat turns information into understanding that actually sticks.Powered by our Qwen3-Max model and grounded in cognitive psychology it designs a learning path tailored to the way you think. ✅ Guides you through Socratic-style dialogue instead of just giving you answers ✅ Adapts to your current level like a tutor who always works in your optimal learning zone ✅ Builds mental scaffolds so you can handle complex logic without feeling overwhelmed Unlock your potential not just the answer key. 🧬 ✨Try it"
X Link 2025-12-11T13:27Z 126.9K followers, 133.7K engagements