Qwen(@Alibaba_Qwen)

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

💬98🔄51❤️1549👀168506📊188

⚡ 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

💬72🔄58❤️633👀68017📊168

⚡ 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❤️712👀71858📊100

⚡ 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🔄106❤️1234👀111850📊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

💬271🔄571❤️6014👀1182096📊1064

⚡ 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❤️337👀71380📊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❤️2091👀149726📊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❤️263👀40013📊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👀46365📊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❤️164👀32344📊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❤️717👀71514📊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🔄97❤️1548👀112425📊209

⚡ 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❤️258👀35982📊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❤️227👀27108📊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👀46135📊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

⚡ Powered by xgo.ing

At a 1M-token context length, QSA’s attention kernel is up to 7.6× faster in prefill and 4.9× faster...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 12:34:04 GMT

At a 1M-token context length, QSA’s attention kernel is up to 7.6× faster in prefill and 4.9× faster in decode. With a 90% prefix-cache hit rate, Qwen3.8-Flash-Next delivers 8.6× the prefill throughput of Qwen3.7-Plus.

💬2🔄14❤️302👀38994📊34

⚡ Powered by xgo.ing

With only 6B active parameters, Qwen3.8-Flash-Next-Base tops 8 of 14 benchmarks, including MMLU-Pro,...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 12:34:04 GMT

With only 6B active parameters, Qwen3.8-Flash-Next-Base tops 8 of 14 benchmarks, including MMLU-Pro, SuperGPQA, BBH and GSM8K. And it remains competitive with Qwen3.7-Plus-Base on the rest. Its 51B N-gram embedding parameters use deterministic lookups, adding no per-token matrix-multiplication cost.

💬7🔄21❤️320👀69410📊44

⚡ Powered by xgo.ing

Model Architecture Four core upgrades for maximum capability, efficiency, capacity, and stability: ...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 12:34:03 GMT

Model Architecture

Four core upgrades for maximum capability, efficiency, capacity, and stability:

- Attention: GDN + QSA Hybrid. Gated DeltaNet (GDN) compresses history. Qwen Sparse Attention (QSA) uses a lightweight indexer for micro-block context selection. Lower the cost of attention on long sequences.
- Residual: Gated Residual (GR) widens the residual stream to 4 branches with a dynamic read and write gating, strengthening cross-layer information flow and significantly improving training stability.
- Embedding: N-gram Embedding uses local context lookups to expand model capacity at minimal compute cost, while keeping the embedding table in host memory with asynchronous prefetching.
- Optimization: Muon optimizer. Refines Muon through improved orthogonalization, smarter parameter assignment between Muon and AdamW, and fused-parameter splitting, with scaling laws refitted for the new architecture.

💬6🔄43❤️460👀88080📊72

⚡ Powered by xgo.ing

Language performance & Vision Language performance:

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 12:34:02 GMT

Language performance & Vision Language performance:

💬14🔄45❤️620👀165689📊102

⚡ Powered by xgo.ing

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

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 12:34:01 GMT

⚡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

💬441🔄1032❤️7824👀1854297📊1690

⚡ Powered by xgo.ing

#1 among open models in the Image-to-WebDev Arena, #7 overall. 🚀 Thanks for the recognition! @arena...

Qwen (@Alibaba_Qwen) — Wed, 26 Aug 2026 05:49:40 GMT

#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!

🔗 View Quoted Tweet

💬66🔄54❤️801👀71022📊115

⚡ Powered by xgo.ing

Open models, open science. Qwen keeps growing steadily, and we'll always be right here with the rese...

Qwen (@Alibaba_Qwen) — Tue, 25 Aug 2026 03:25:21 GMT

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.

🔗 View Quoted Tweet

💬33🔄32❤️643👀50805📊76

⚡ Powered by xgo.ing

Qwen3.8-27B at #9 overall on Code Arena, the only model in its size class in the top 10.😎 Small but...

Qwen (@Alibaba_Qwen) — Tue, 25 Aug 2026 03:24:57 GMT

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.

🔗 View Quoted Tweet

💬62🔄95❤️1405👀115197📊170

⚡ Powered by xgo.ing

Fresh recipes just dropped! ⚡ NVFP4 + DFlash2 for Qwen3.8-27B now in the SGLang cookbook. Thanks for...

Qwen (@Alibaba_Qwen) — Fri, 21 Aug 2026 07:58:00 GMT

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 🫡

🔗 View Quoted Tweet

💬46🔄50❤️846👀90518📊137

⚡ Powered by xgo.ing

Huge thanks to Unsloth for the great work. This is wonderful news for the community! 🥳Qwen3.8-27B, ...

Qwen (@Alibaba_Qwen) — Thu, 20 Aug 2026 04:06:14 GMT

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: https:/unsloth.ai/docs/basics/dy…https://t.co/xIdNwm7CLQ

🔗 View Quoted Tweet

💬53🔄120❤️2067👀144773📊253

⚡ Powered by xgo.ing

Great UI starts with good code. Give Qwen3.8-Max a try on Kilo! 👀 @kilocode

Qwen (@Alibaba_Qwen) — Thu, 20 Aug 2026 03:55:36 GMT

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.

🔗 View Quoted Tweet

💬23🔄12❤️230👀33678📊34

⚡ Powered by xgo.ing

#1 open-weight model on Harvey's Legal Agent benchmark! 🙌 Strong enough to handle professional task...

Qwen (@Alibaba_Qwen) — Wed, 19 Aug 2026 03:47:30 GMT

#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.

🔗 View Quoted Tweet

💬54🔄60❤️1229👀75769📊149

⚡ Powered by xgo.ing

4 days to the top.🏆Thank you to every builder who pushed Qwen3.8-27B to #1 on Cline! @cline

Qwen (@Alibaba_Qwen) — Wed, 19 Aug 2026 03:35:18 GMT

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.

🔗 View Quoted Tweet

💬47🔄31❤️737👀50961📊90

⚡ Powered by xgo.ing

One prompt, one shot. Qwen3.8-27B creates something incredible. 😎Now it's your turn to run it on yo...

Qwen (@Alibaba_Qwen) — Tue, 18 Aug 2026 06:38:05 GMT

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.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬60🔄26❤️677👀71516📊97

⚡ Powered by xgo.ing

Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it...

Qwen (@Alibaba_Qwen) — Tue, 18 Aug 2026 06:15:40 GMT

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! 🤯

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬52🔄81❤️1491👀89984📊172

⚡ Powered by xgo.ing

A local 27B model scoring frontier performance! Huge thanks to @cline for the shoutout.🥳 This is ju...

Qwen (@Alibaba_Qwen) — Tue, 18 Aug 2026 04:15:44 GMT

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.

🔗 View Quoted Tweet

💬116🔄164❤️2958👀132822📊330

⚡ Powered by xgo.ing

🚀Qwen3.8-27B flies on a laptop, becoming part of our work and daily lives. Thanks for the shoutout!...

Qwen (@Alibaba_Qwen) — Sun, 16 Aug 2026 07:32:09 GMT

🚀Qwen3.8-27B flies on a laptop, becoming part of our work and daily lives. Thanks for the shoutout! @atomic_chat_hq

💬84🔄131❤️2003👀200009📊356

⚡ Powered by xgo.ing

3000000000 downloads! Can you count the zeros at a glance? 😎 Thank you all for the incredible love....

Qwen (@Alibaba_Qwen) — Sun, 16 Aug 2026 06:50:18 GMT

3000000000 downloads! Can you count the zeros at a glance? 😎 Thank you all for the incredible love. Let's keep growing together! 🌱

💬124🔄192❤️3468👀422679📊466

⚡ Powered by xgo.ing

Huge thanks to the whole community! Qwen3.8-27B is now the #1 trending model on Hugging Face! 🏆 Try...

Qwen (@Alibaba_Qwen) — Sun, 16 Aug 2026 06:34:09 GMT

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

🔗 View Quoted Tweet

💬179🔄144❤️3362👀212675📊391

⚡ Powered by xgo.ing

Laptop-size model, frontier-size leap. 🏃‍♀️Qwen3.8-27B is live on LM Studio. Try it! @lmstudio

Qwen (@Alibaba_Qwen) — Sat, 15 Aug 2026 03:42:11 GMT

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…K

🔗 View Quoted Tweet

💬61🔄55❤️866👀80924📊121

⚡ Powered by xgo.ing

Qwen3.8-27B is now part of your everyday life — from smartphones to vehicles. ⚡️🚀Appreciate your w...

Qwen (@Alibaba_Qwen) — Sat, 15 Aug 2026 03:28:41 GMT

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.

🔗 View Quoted Tweet

💬17🔄35❤️585👀54404📊62

⚡ Powered by xgo.ing

Ready right now! 😎Incredible to see Qwen3.8-27B fly on RTX Spark. Download, deploy and create somth...

Qwen (@Alibaba_Qwen) — Sat, 15 Aug 2026 03:22:01 GMT

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.

🔗 View Quoted Tweet

💬23🔄29❤️669👀66835📊73

⚡ Powered by xgo.ing

Qwen3.8-27B is available on @ollama ！Any harness you run, the model always delivers. Let's code tog...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 17:44:00 GMT

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

🔗 View Quoted Tweet

💬34🔄47❤️643👀91773📊82

⚡ Powered by xgo.ing

Small models, big real-world impact. Proud to see Qwen leading local inference in the State of Open...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 17:05:54 GMT

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-…H

🔗 View Quoted Tweet

💬23🔄31❤️601👀43662📊63

⚡ Powered by xgo.ing

Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 16:58:21 GMT

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👇
lightseek.org/blog/tokenspee…T

🔗 View Quoted Tweet

💬6🔄9❤️211👀30239📊22

⚡ Powered by xgo.ing

From idea to implementation in one go.🏃‍♀️ Max-level intelligence, served fresh on Day 0. Qwen3.8-...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 16:50:51 GMT

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 cosiliconflow.comfZQsY 🍳

🔗 View Quoted Tweet

💬6🔄7❤️225👀29195📊22

⚡ Powered by xgo.ing

Max-level intelligence, one API call away. Qwen3.8-2.4T-A95B is now live on DeepInfra, ready for you...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 16:27:57 GMT

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

🔗 View Quoted Tweet

💬11🔄15❤️226👀26445📊27

⚡ Powered by xgo.ing

🎁A gift for developers: Qwen3.8-27B, running locally on AMD from day zero. Appreciate the work fro...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 16:18:12 GMT

🎁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: amd.com/en/blogs/2026/…

🔗 View Quoted Tweet

💬26🔄44❤️743👀64364📊84

⚡ Powered by xgo.ing

27B on 17GB RAM. Are you ready to create something incredible? 😎 Thanks for highlighting it! @Unslo...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 16:07:58 GMT

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…

🔗 View Quoted Tweet

💬112🔄403❤️5676👀475268📊791

⚡ Powered by xgo.ing

Yes, we are back👑, with 206 tok/s on a single RTX 5090! Amazing Day-0 work from the SGLang team. Gi...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 15:55:40 GMT

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 👇

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬95🔄422❤️6846👀436487📊794

⚡ Powered by xgo.ing

One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!👍 Try Qwe...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 15:50:30 GMT

One GPU, 1M context, Day-0 ready. Big props to the vLLM team for the seamless integration!👍
Try Qwen3.8-27B on vLLM: @vllm_projectrecipes.vllm.ai/Qwen/Qwen3.8-2…c

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+.

recipes.vllm.ai/Qwen/Qwen3.8-2…93x

🔗 View Quoted Tweet

💬21🔄53❤️1084👀70706📊113

⚡ Powered by xgo.ing

Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean a...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 15:35:17 GMT

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/45VBAyZdU

One API, usage-based pricing, no infra to manage.

Your browser does not support the video tag.

🔗 View on Twitter

🔗 View Quoted Tweet

💬6🔄8❤️184👀22896📊19

⚡ Powered by xgo.ing

Qwen 3.8-Max is live on Modal, with the full 1M context window and a custom DFlash speculator under ...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 15:32:05 GMT

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.

🔗 View Quoted Tweet

💬13🔄37❤️414👀40607📊49

⚡ Powered by xgo.ing

Qwen3.8-Max is coming to Nebius Token Factory on Day 0. Great to kick things off together with Nebiu...

Qwen (@Alibaba_Qwen) — Fri, 14 Aug 2026 15:28:16 GMT

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

💬9🔄16❤️189👀36220📊30