@Alibaba_Qwen
Open foundation models for AGI.
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
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…
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.
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…
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: t.co/qsFWpRIHEK
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… GGUF: huggingface.co/unsloth/Qwen3.… x.com/Alibaba_Qwen/s…
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!👀👇 - Blog: t.co/M5hYypFLgJ - Technical Report: t.co/IF0gObIkQO - Hugging Face: t.co/6ow8QVAABt - ModelScope: t.co/tDOn2jNuFG
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👇
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! 🙌 🔗 t.co/NPnI6LNrGA
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…
⚡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!👀👇 - Blog: t.co/M5hYypFLgJ - Technical Report: t.co/IF0gObIkQO - Hugging Face: t.co/6ow8QVAABt - ModelScope: t.co/tDOn2jNuFG
Language performance & Vision Language performance:
#1 among open models in the Image-to-WebDev Arena, #7 overall. 🚀 Thanks for the recognition! @arena Just 27B parameters, on par with models 100x its size. Now, can you guess what surprise we're dropping tonight? 👀
Arena.ai@arena·Big news: Qwen3.8-27B by @Alibaba_Qwen is now #1 among open models in the Image-to-WebDev Arena (#7 overall)! Priced at $0.40/$3 per M input/output tokens, it has shifted the Pareto frontier (more info below). Qwen3.8-27B has 1574 pts with 27B parameters, achieving performance on par with Kimi K3 (Max) at 2.8T parameters! Congrats to @Alibaba_Qwen on this contribution to the open model ecosystem!
Open models, open science. Qwen keeps growing steadily, and we'll always be right here with the research community.🙌 Thanks for the deep dive! @natolambert
Nathan Lambert@natolambert·Over the weekend I had Codex parse 500K arXiv AI/ML papers since ChatGPT to understand which open models are used for research. In 2024, ~30% of papers mentioned an American open model and only 10% a Chinese model. Today, ~40% of papers mention a Chinese (open) LLM, and only 25-30% an American one. Chinese models are the default for research. Chinese mentions are still growing while American open models are stagnating. When looking at this data it's important to remember that papers substantially lag model releases, as research takes a long time. Qwen's steady growth is reflective of this, but so is Llama's lasting power. Some more observations: 1. Qwen has been steadily growing, and today 1/3 of papers which mention any LLM mention qwen. OpenAI's closed models are the highest overall, at ~37%. 2. Llama peaked around April of 2025 at 30% of papers which mention any LLM (including ChatGPT etc). Llama 4 was released at about the same time, and Llama has been declining since. 3. Gemini and Claude are less common than the leading open models, mentioned in 10-15% of papers puts them behind all of Qwen, Llama, and DeepSeek. Open models should be and are the foundations of open research. The % of papers mentioning any LLM have been steadily climbing since 2023. | Year | January | April | July | October | | 2023 | 10.43% | 15.39% | 18.69% | 32.18% | | 2024 | 29.70% | 33.93% | 35.70% | 44.25% | | 2025 | 39.23% | 45.28% | 44.94% | 53.52% | | 2026 | 55.49% | 57.26% | 53.14% | TBD Now over 50% of AI papers, from 10% in 2023. Other notes: - Gemma and Mistral hover around 5-10%. - Our beloved fully-open Olmo models have been ~1% since the first release in Jan. 2024. - DeepSeek has a clear jump after R1 in Jan. 2025 - Data derived from the most popular ML arXiv categories: cs. AI, cs. CL, cs. CV, cs. LG, stat. ML Just like our downloads and derivative model data, this is updated daily on the Interconnects Open Model Dashboard.
Qwen3.8-27B at #9 overall on Code Arena, the only model in its size class in the top 10.😎 Small but mighty. Thanks for the recognition! @arena
Arena.ai@arena·Exciting news: Qwen3.8-27B by @Alibaba_Qwen just landed in Code Arena: WebDev at #9 overall with 1595 pts. It is the only model in its size class in the top 10, and also reshapes the Pareto Frontier! It is only 6 ranks behind the much larger Qwen3.8-Max. For scale: Gemma 4-31B which was released back in April sits at #80. Congrats to @Alibaba_Qwen on the release! See thread for more highlights on Qwen3.8-27B.
Fresh recipes just dropped! ⚡ NVFP4 + DFlash2 for Qwen3.8-27B now in the SGLang cookbook. Thanks for the support! @sgl_project
SGLang@sgl_project·Just pushed DFlash2 (@inco_ai) recipes to the Qwen3.8 27B cookbook⚡️ docs.sglang.io/cookbook/autor… The community has been seeing great results with NVFP4 + DFlash2, and these recipes should be some very good starting points to play with. More Qwen3.8 27B updates on the way 🫡 x.com/sgl_project/st…
Huge thanks to Unsloth for the great work. This is wonderful news for the community! 🥳Qwen3.8-27B, smaller and sharper than ever. Let's try it! @UnslothAI
Unsloth AI@UnslothAI·We’re releasing new Qwen3.8-27B GGUFs with 10% higher accuracy. Unsloth Dynamic V3 outperforms others by >10% on Div-300, KLD & more benchmarks. We also release 1-bit quants that retain 77% accuracy. Run on 8GB RAM. Blog: unsloth.ai/docs/basics/dy… GGUF: huggingface.co/unsloth/Qwen3.… x.com/UnslothAI/stat…
Great UI starts with good code. Give Qwen3.8-Max a try on Kilo! 👀 @kilocode
Kilo (acq. by Anaconda)@kilocode·Qwen3.8-Max landed #4 on Arena's Frontend Code leaderboard — one spot above Claude Fable 5. We ran both on the same 10 UI design prompts, one shot each, to see how close that really is.
#1 open-weight model on Harvey's Legal Agent benchmark! 🙌 Strong enough to handle professional tasks. Small enough to run on your local machine. Qwen3.8-27B is becoming part of your everyday workflows.🧑💻
Vals AI@ValsAI·On @harvey's Legal Agent, it is tied with Fable 5 at 11.3pts and is ahead of Kimi K3, Qwen 3.8 Max, and DeepSeek V4.
4 days to the top.🏆Thank you to every builder who pushed Qwen3.8-27B to #1 on Cline! @cline
Cline@cline·Qwen3.8-27B is now the #1 local model in Cline after just 4 days. This ends a *4 month* streak by the previous winner Qwen2.5-Coder-7B which has been the top local model since April. x.com/cline/status/2…
One prompt, one shot. Qwen3.8-27B creates something incredible. 😎Now it's your turn to run it on your own laptop. Can't wait to see what you come up with!👀@ItsmeAjayKV
AJ@ItsmeAjayKV·Here's a comparison i never thought i would make Qwen-3.8-27b vs Gemini-3.7-flash Yes, you read it right! I don't know what to say, this is soo damn impressive. the difference is hugeee🤯 Take a look at this result 😍 (watch it in highest quality) Same prompt, both one shot on web-chat ui Qwen-3.8-27b produces consistent beautiful, visually stunning results. This is one of the best water surface simulations i have seen across every local models i have run and at the same time beating Gemini-3.7-flash result. And this is running on my 3090. And yes its Q5, not even f8.
Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it can do! ⚡
Xenova@xenovacom·It's official: Qwen3.8-27B just scored 52 on the @ArtificialAnlys Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯
A local 27B model scoring frontier performance! Huge thanks to @cline for the shoutout.🥳 This is just the beginning — Qwen3.8-27B will keep finding its way into more fields.🌱
Cline@cline·Artificial Analysis Intelligence Index puts Qwen3.8-27B at DeepSeek V4-Pro and GPT 5.6 Luna performance. This is the first time a local model has scored frontier model capability. We weren’t expecting this pace of local progress anywhere near this soon.
🚀Qwen3.8-27B flies on a laptop, becoming part of our work and daily lives. Thanks for the shoutout! @atomic_chat_hq
atomic.chat@atomic_chat_hq·Run Qwen3.8 27B locally via Atomic Chat💥 We released Atomic Dynamic GGUF quants, from 8-bit (28.9 GB) down to 1-bit (8.5 GB), and measured all other Qwen3.8 GGUFs in the community AD-IQ3_S runs on a 16GB MacBook Air and picks the same next token as the BF16 original 92.4% of the time
3000000000 downloads! Can you count the zeros at a glance? 😎 Thank you all for the incredible love. Let's keep growing together! 🌱
Bloomberg@business·Alibaba's open-weight models have accumulated more than 3 billion global downloads in the past six months, eclipsing Meta, Alphabet and domestic peers to become the world’s No. 1 artificial-intelligence model bloomberg.com/news/articles/…
Huge thanks to the whole community! Qwen3.8-27B is now the #1 trending model on Hugging Face! 🏆 Try it out and let us know what you think. 🤗
Julien Chaumond@julien_c·soon 10k
Laptop-size model, frontier-size leap. 🏃♀️Qwen3.8-27B is live on LM Studio. Try it! @lmstudio
LM Studio@lmstudio·Qwen3.8-27B is here! 🚀 It's a leap in capabilities for a laptop size model. Requires ~17GB to run locally. Model page: lmstudio.ai/qwen/qwen3.8-2… x.com/Alibaba_Qwen/s…
Qwen3.8-27B is now part of your everyday life — from smartphones to vehicles. ⚡️🚀Appreciate your work! @MediaTek
MediaTek@MediaTek·Congratulations to the @Alibaba_Qwen on the launch of Qwen 3.8! MediaTek continues our long-standing collaboration with Qwen, with Day-0 support now available on Dimensity Auto Cockpit C-X1 and the latest Dimensity flagship mobile SoC, bringing smarter and more intuitive on-device AI experiences to more people, from smartphones to vehicles, and helping make agentic AI a seamless part of everyday life.
Ready right now! 😎Incredible to see Qwen3.8-27B fly on RTX Spark. Download, deploy and create somthing new. @NVIDIARTXSpark
NVIDIA RTX Spark@NVIDIARTXSpark·Ready to run Qwen3.8 locally? 👀 Qwen3.8-27B packs powerful AI into an open model developers can download, serve locally, and build with on their own terms. x.com/17533392773863…
Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code together, and show us what you build.😎
ollama@ollama·Qwen 3.8 27B is now available on Ollama. It's one of the best open models at this size, and made for agentic tasks and professional work. Try it directly with the apps & harnesses you use: Claude Code: ollama launch claude --model qwen3.8 OpenCode: ollama launch opencode --model qwen3.8 Hermes Agent: ollama launch hermes --model qwen3.8 Pi: ollama launch pi --model qwen3.8 We have also optimizations for Apple Silicon! Try it with the model name: qwen3.8:27b-mlx
Small models, big real-world impact. Proud to see Qwen leading local inference in the State of Open Models. Enjoy the sunshine from Qwen.☀️ 😎 Appreciate your work! @huggingface
Hugging Face@huggingface·The State of Open Models, Summer 2026 ☀️ frontier models are getting larger, but small models still dominate real-world usage. Qwen leads local inference, followed by Gemma. AI agents are becoming a major force on the Hub Full picture on the blog 🤗 huggingface.co/blog/state-of-…
Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to LightSeek for the fantastic Day-0 support! @lightseekorg
LightSeek Foundation@lightseekorg·We’re proud to be the Day 0 open-source inference engine partner for @Alibaba_Qwen 3.8. To serve this 2.4T-parameter model across multi-node @NVIDIAAI Blackwell inference, we optimized DP/EP scaling across nodes, delivering 30%+ faster performance than TP16, plus DSpark speculative decoding with single CUDA graph optimization👇 t.co/Ec62BNvDyT
From idea to implementation in one go.🏃♀️ Max-level intelligence, served fresh on Day 0. Qwen3.8-2.4T-A95B is live on SiliconFlow. Thanks! @SiliconFlowAI
SiliconFlow@SiliconFlowAI·🚀 Day-0 Support! @Alibaba_Qwen has open-sourced Qwen3.8-2.4T-A95B — and it’s now live on SiliconFlow. ⚡ With 2.4T parameters and 95B active, Qwen3.8 is built to take a goal and come back with finished work — coding, researching, planning, and executing along the way. 💸 Per 1M tokens: • Input: $2.00 • Output: $6.00 • Cached input: $0.25 💻 Autonomous coding. 🔬 Deep research. 🤖 End-to-end agent execution. Built for serious workloads — from idea to implementation in one go. Time to cook → t.co/P1QJ3fZQsY 🍳
Max-level intelligence, one API call away. Qwen3.8-2.4T-A95B is now live on DeepInfra, ready for your creative builds. 🥳 Take a deep dive on DeepInfra! @DeepInfra
DeepInfra@DeepInfra·New on DeepInfra: Qwen3.8-2.4T-A95B 🚀 @Alibaba_Qwen's latest sparse MoE — 2.4T total params, 95B active, 512 experts. Built for coding, agentic workflows, and complex reasoning, with native 262K context. Live now at $2.00/M in · $6.00/M out · $0.20/M cached @Alibaba_Qwen @alibaba_cloud
🎁A gift for developers: Qwen3.8-27B, running locally on AMD from day zero. Appreciate the work from the AMD team! @AMD
AMD@AMD·Qwen3.8 27B brings a new state-of-the-art dense model for local AI development. ⚡ Run it on AMD Ryzen™ AI Max+ processors or single Radeon™ AI PRO R9700 card ⚡ Experience it with @LMStudio ⚡ Turn it into an app with @lemonade_server Start building with AMD Day 0 support for @Alibaba_Qwen now: t.co/EQKk02BmbY
27B on 17GB RAM. Are you ready to create something incredible? 😎 Thanks for highlighting it! @UnslothAI
Unsloth AI@UnslothAI·Qwen3.8-27B can now be run locally! ✨ Run on 17GB RAM via Unsloth Dynamic GGUFs. Qwen3.8-27B is by far the strongest model for its size. We also uploaded NVFP4 quants. GGUF: huggingface.co/unsloth/Qwen3.… Guide: unsloth.ai/docs/models/qw… x.com/Alibaba_Qwen/s…
Yes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from the SGLang team. Give it a try~@sgl_project
SGLang@sgl_project·The king of small models is back! Qwen3.8-27B from @Alibaba_Qwen is open source, and Day-0 support is live in SGLang: - 206.1 tok/s decode on a single RTX 5090, with our NVFP4 plus DSpark - 38.28 tok/s decode on DGX Spark Qwen3.8-27B raises the bar again for what a small model can do on agentic planning and long-horizon tasks. Long live the (small model) king! Run it locally with SGLang 👇
One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!👍 Try Qwen3.8-27B on vLLM: @vllm_project recipes.vllm.ai/Qwen/Qwen3.8-2…
vLLM@vllm_project·🎉 Qwen3.8-27B is here from @Alibaba_Qwen, and the whole thing fits on a single GPU. Same hybrid backbone as the 2.4T flagship, dense instead of MoE. Day-0 support in vLLM. 🚀 What is in it for serving ✨ - Fits one Blackwell GPU in every precision. Qwen ships BF16 and FP8, the NVFP4 build from @inferact - 262K native context, stretching to 1M. At that length one GB300 still has room for roughly 6.6M KV tokens. Six full-length sequences in flight, on one GPU - An MTP draft head rides inside the checkpoint, so speculative decoding needs no separate speculator repo. Acceptance on short prompts measured 92.2% in BF16 and 84.8% in FP8 Verified end-to-end on @NVIDIA GB300: BF16 and FP8 at TP4, NVFP4 at TP1, tool calls working, correct generations at 1M context. Two prerequisites, vLLM nightly and transformers 5.8.0+. 🔗 t.co/gSHtqxi93x
Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean as our Day 0 launch partner. Big model. Smooth sailing. Now on DigitalOcean.🌊🏄♀️ @digitalocean
DigitalOcean@digitalocean·Now available: @Alibaba_Qwen 3.8-2.4T-A95B from @alibaba_cloud on DigitalOcean Serverless Inference via NVIDIA HGX™ B300 GPUs. 🤖 1M context, built for long-horizon coding. 🔗 do.co/45VBAyZ One API, usage-based pricing, no infra to manage.
Qwen 3.8-Max is live on Modal, with the full 1M context window and a custom DFlash speculator under the hood. Love seeing our launch partner Modal go all in from Day 0!⚡️ 2.4T parameters. 1M context. Somehow, still just a Modal call away. @modal
Modal@modal·Qwen3.8-2.4T-A95B by @Alibaba_Qwen and @alibaba_cloud is now available on Modal. Served with a custom DFlash speculator trained on tool-call-heavy data. Full 1M context window.
Qwen3.8-Max is coming to Nebius Token Factory on Day 0. Great to kick things off together with Nebius as our Day 0 launch partner, bringing dedicated inference to more users. Big model, right from the start.🔥@nebiustf
Nebius Token Factory@nebiustf·Qwen3.8-2.4T-A95B is going open weight: 2.4T parameters, with 95B active, and Nebius Token Factory is joining as a Day 0 launch partner. Qwen3.8-2.4T-A95B is coming to Nebius Token Factory Managed Services for dedicated inference. @Alibaba_Qwen @alibaba_cloud
Qwen3.8-Max is live on Fireworks, ready for agents, heavy coding, and long-context work. Fireworks is right there with us as a Day 0 launch partner. What a way to kick things off!It's Day 0, cue the Fireworks! 🎉🎆@FireworksAI_HQ
Fireworks@FireworksAI_HQ·Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, large context windows, and is ideal for coding and agentic performance. Start building today: fireworks.ai/models/firewor…
Qwen3.8-Max is live on Together AI. Together AI is with us as a Day 0 launch partner, and we couldn’t ask for a better name to share Day 0 with. 2.4T parameters, 95B active, 1M context — all together now. 🧑🤝🧑@togethercompute
Together AI@togethercompute·Qwen3.8-2.4T-A95B is live on Together AI. The Qwen team’s new open-weight MoE packs 2.4T total parameters with 95B active, a 1M context window, and strong coding & agent capabilities. Start building: together.ai/models/qwen3-8…
Qwen3.8-Max is live on Fireworks, ready for agents, heavy coding, and long-context work. Fireworks is right there with us as a Day 0 launch partner. What a way to kick things off!It's Day 0, cue the Fireworks! 🎉🎆
Fireworks@FireworksAI_HQ·Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, large context windows, and is ideal for coding and agentic performance. Start building today: fireworks.ai/models/firewor…
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows. - 262K native context, easily extendable to 1M tokens via YaRN. - Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0. 🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently. Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now! Download, deploy, and build something we haven't imagined yet. 👀👇 - Hugging Face： t.co/4kaAcqYEVj - ModelScope： t.co/eRIMZCGkhC
Performance of Qwen3.8-27B:
Less than 2 hours to say hi👋. It's almost time! See you soon: 👀 huggingface.co/Qwen/Qwen3.8-2…
Qwen Live now, an appetizer 👀
QwenCloud@qwen_cloud·Ready for Qwen Live EP2？We will start at 10:00AM！ UTC+8 x.com/i/broadcasts/1… Qwen Cloud：qwencloud.com/?utm_content=g… #QwenCloud
Try Qwen-Image-3.0 on @openart_ai! 🎨👀
OpenArt@openart_ai·Qwen Image 3.0 is now on OpenArt ✨ The most Real Qwen image model yet. Native text across 12 languages, precise 10px type, and full interfaces like web pages, games, and livestreams rendered with real world knowledge. Available now on OpenArt: openart.ai/suite/create-i…
From #22 to #4 on Legal Research Bench! Solid progress for Qwen3.8-Max. Thanks for highlighting~✨
Vals AI@ValsAI·Qwen 3.8 Max nearly doubled its score on Legal Research Bench in under three months, climbing from #22 to #4.
👀 Seeing is just the beginning. With Qwen-MM-Plugins, turn your favorite agent harness multimodal-native — read images, videos & documents, edit videos, work with 3D/CAD, and more. From multimodal models → multimodal agents. 🚀 Watch it in action: github.com/QwenLM/Qwen-MM…
The cloud was always a cat. Qwen3.8-Max just saw it first. 😼☁️ Try it yourself! x.com/ann_nnng/statu…
Thanks for the thorough testing! With Qwen3.8-Max, everyone can observe the world in detail. 👀 x.com/skalskip92/sta…
A quick snapshot of where Qwen3.8-Max stands today: Qwen3.8-Max now ranks #5 on the Artificial Analysis Intelligence Index, and #1 on the Agentic Index!🥇 We'll keep pushing forward. 🚀
Let's create with Qwen-Image-3.0-Pro on fal! 🎨 x.com/fal/status/208…
Try npm i -g cline on Cline!👀
Qwen3.8-Max hits #2 in Image-to-WebDev Arena! It sees, it builds~😎 x.com/arena/status/2…
Qwen-Image-3.0-Pro is live on Qwen Cloud now! Try it out👇 qwencloud.com/models/qwen-im… x.com/qwen_cloud/sta…
Qwen3.8-Max is available in Hermes Agent now! Let's build! 🚀🚀 x.com/NousResearch/s…
Qwen-Image-3.0-Pro has made a massive leap from the previous generation, now ranking #5 globally. Appreciate the recognition! We will keep building.🚀 x.com/arena/status/2…
Qwen3.8-Max, better and cheaper. Try it out. 👀 x.com/CommandCodeAI/…
Appreciate it! High performance, low cost. Try it out today. 💻 x.com/vercel_dev/sta…
Live and ready to build. Thanks for having us! @OpenRouter. Open weights dropping soon.⚡️ x.com/OpenRouter/sta…
Ask anything, anonymously. Qwen3.8-Max has landed on Venice. Give it a try! x.com/AskVenice/stat…
Live in Command Code!🎉 x.com/CommandCodeAI/…
Let's Go!🚀 x.com/opencode/statu…
Appreciate it! Now let's understand the world through the eyes of Qwen3.8. 🥳 x.com/arena/status/2…
Thanks for the recognition. We'll keep building! 🚀 x.com/arena/status/2…
🔥Let's talk about Qwen! #AMA x.com/QwenDevs/statu…
🏆 Alibaba hits #2 on the Text Arena.
📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉 Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters: - Autonomous coding: 10+ days of self-evolving development, from empty folder to production without hand-holding, complete project trace in the GitHub：t.co/iVHZWQoeSo - Real work, real results: Production-quality deliverables across hundreds of professions. - Long-horizon mastery: System-level autonomous planning with closed-loop adaptive learning, driving 500+ turns of chip design optimization and 365 days of e-commerce strategy. - Native multimodal intelligence: Vision isn't just input — it's a continuous feedback loop for planning, execution, and self-correction. 💰Pricing: Input: $2.0 / M tokens Output: $6.0 / M tokens Implicit Caching: $0.25 / M tokens Start building with Qwen3.8-Max! 🚀 📖 Blog: t.co/iwjmQxLBof ✅ Qwen Studio: t.co/4V2pFvDovG ⚡ API: t.co/gAGqaLQGbN
LM Performance
Text Arena: arena.ai/leaderboard/te…
Meet Qwen3.8-Max: A New Bar for Coding and Cowork.
Introducing Qwen-Audio-3.0-ASR-Flash: More context-aware. Stronger domain-term recognition. 🚀Our latest ASR model upgrades: • Context consistency • Domain-term recognition • Custom hotwords • Speech polishing into structured transcripts ⚡️In internal tests: • Medical term recall: 95.36% • Industrial term recall: 93.24% Qwen-Audio-3.0-ASR-Flash-Streaming： t.co/QqTp4HkknJ Qwen-Audio-3.0-ASR-Flash-Filetrans: t.co/7llmle4deF Qwen-Audio-3.0-ASR-Flash: t.co/VxruY0Ruhi
Since launching Qwen3.8-Max-Preview, we've received valuable feedback from developers! To help users better explore Qwen3.8's agentic capabilities, we're officially launching the #QwenGrowthPlan today! 🚀 We invite you to: - Use Qwen3.8 to complete your real-world tasks - Submit your good or bad cases to us Every real task is nourishment for Qwen3.8's growth. We've prepared valuable rewards to recognize your active participation. For more detailed participation info and prizes, please check out the posters below👇. Besides emailing us, feel free to share your awesome cases or feedback directly on X and @Alibaba_Qwen Join us and let's grow together!
Since launching Qwen3.8-Max-Preview, we've received valuable feedback from developers! To help users better explore Qwen3.8's agentic capabilities, we're officially launching the #QwenGrowthPlan today! 🚀 We invite you to: - Use Qwen3.8 to complete your real-world tasks - Submit your good or bad cases to us Every real task is nourishment for Qwen3.8's growth. We've prepared valuable rewards to recognize your active participation. For more detailed participation info and prizes, please check out the posters below👇. Besides emailing us, feel free to share your awesome cases or feedback directly on X and @Qwen. Join us and let's grow together!
Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whisper], [angry], [breaths] & [laughs] • Free-style natural-language control-“read this slowly, like a bedtime story” • 16 languages • Clean output even from noisy reference audio • One-pass long-form up to 3 min now #1 on the Artificial Analysis TTS Leaderboard. Blog: t.co/ACqTI2wGHI API: t.co/Xh2Y19noVx
🎨 Meet Qwen-Image-3.0 — the third generation of our foundational image generation model. If 1.0 was about "Precision," and 2.0 added "Variety, Completeness, Beauty & Authenticity," then 3.0 comes down to a single word: Real (实). Three dimensions of "Real": 📰 Rich Content — prompts up to 4.5k tokens. One-pass generation of complex layouts: newspapers, storyboards, exam papers — even a 3×3 infographic grid or picture-in-picture-in-picture UIs. 🔬 Authentic Details — text legible down to 10px, full LaTeX paper pages, pores, hair strands & near-photographic skin texture. 🌏 Deep Knowledge — native rendering in 12 languages, 100+ art styles, realistic UIs (web / games / livestreams), plus world knowledge & live web retrieval. Not just "good-looking" — genuinely useful. Image generation as a real productivity tool for design, content, education & e-commerce. Go create 🏃🎨 💬Qwen Chat: t.co/941HmITJ2W 📝Blog: t.co/5mnS4uI9Ar
Horizontal expansion reflects the model's strength in semantic juxtaposition and spatial control — laying out multiple concepts within a single image without mutual interference. With just 3.7k tokens, the model renders a 3×3 infographic across 9 domains: tunnel safety comic, spatial geometry, stylistic analysis of Chu Shi Biao, projectile motion, parasitology, chest-pain diagnostics, Sylow theorems, bank internal-control, and DNA structure — every cell precise in text and visuals.
During Preview, Qwen3.8 is getting better by the day. Latest version is live now, with broad gains and a big step up on web frontend. Thank you all — the response to Qwen3.8-Max-Preview blew us away. 🫶🫶 Qwen3.8 is still evolving daily. Come test it, and tell us what breaks. We're looking forward to a more capable, official version — and to open-weight it for everyone.🚀🚀
Qwen3.8 is launching and going open-weight soon!🌐 With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5. You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out. Can't wait to hear what you build. Stay tuned! 🚀 Token Plan international：t.co/YRvcGdB9Bv China：t.co/PKMUNwUuRp
Qwen3.8 is launching and going open-weight soon!🌐 With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5. You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out. Can't wait to hear what you build. Stay tuned! 🚀 Token Plan international：t.co/YRvcGdB9Bv China：t.co/PKMUNwUuRp
📊 AgentWorldBench: 7-domain benchmark with ground-truth observations from real environments, constructed from 5 frontier model trajectories on 9 established benchmarks. Results: Qwen-AgentWorld-397B-A17B achieves the highest overall score (58.71), outperforming Claude Opus 4.8 (56.59), GPT-5.4 (58.25), and Gemini 3.1 Pro (54.57). For Qwen-AgentWorld-35B-A3B, LWM training lifts Qwen3.5-35B-A3B by +8.66 points (47.73 → 56.39), surpassing Claude Sonnet 4.6 (56.04).
Part II: Investigating the Role of World Modeling in Agent Training 🔬 Paradigm I — Decoupled Simulation: world model as environment simulator for agent RL. The key is controllability: 1️⃣ Zero-shot generalization to 4k OOD OpenClaw environments → +4.3 Claw-Eval, +7.1 QwenClawBench 2️⃣ Controlled Sim RL on MCP → +12.3 MCPMark (uncontrolled: only +3.1) 3️⃣ Sim RL surpasses Real RL against a live search engine: 50.3% vs 45.6% F1 4️⃣ Agents trained in fully fictional, self-consistent worlds generalize to real tasks Controllable simulation shapes agent behavior in ways real environments structurally cannot.
