Aquaduck

The future of intelligence in little machines. Invite-only.

@supermodellabs

[Aquaduck @aquaduckai]

@downloadlos The fact you used AI to break up with AI

[Aquaduck @aquaduckai]

We land in San José tomorrow with @supermodellabs .

WeAreDevelopers World Congress North America kicks off September 23rd.

Find us at Booth 10 all three days.

https://t.co/r3L3eMZKEP
#wearedev

[Zixuan Li @ZixuanLi_]

ZCode is now open source, and the reported security issues have been addressed.
https://t.co/Bq5B6nEnWM

We take the community’s feedback very seriously and apologize for the concern and frustration these issues have caused. We have been working closely with the ZCode team to investigate and remediate the issues raised.

Independent security reviews by third-party firms are now underway. We will share the findings and provide further updates as they become available.

We sincerely appreciate the developer community’s feedback and continued scrutiny. We will continue to monitor the review process closely and provide updates.

[Alibaba Cloud @alibaba_cloud]

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

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

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

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

- Blog: https://t.co/LOEmRCZEzE
- GitHub: https://t.co/S2Xx5xrf4m
- Model Scope: https://t.co/2pqoafYf8I
- Hugging Face: https://t.co/yUblX4MsS3

[WeAreDevelopers @WeAreDevs]

There's a lot happening at WeAreDevelopers, and we're just 48 hours from the World Congress North America 🤯

To make sure you don't miss a thing, here's a little roundup of what happened last week 👇

https://t.co/aUTDGKYT2z

[Kirah Sapong @kirahsapong]

We’re doing this at Aquaduck, plus you can point multiple devices' localhosts at the same endpoint for better collaboration

[OpenAI @OpenAI]

We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12.

We know that the people most affected by this decision are the developers who rely on OpenAI models in Cursor. We care about their experience in this transition and we’re ready to go above and beyond to support them.

https://t.co/OzuCTzUjfX

[Aquaduck @aquaduckai]

@134Ceros @Alibaba_Qwen @UnslothAI 25 tok/s on a single big machine, 15 tok/s on two smaller machines connected over internet. Further speedups on the way. 🫡

[MAZE @remvze]

New OG images on https://t.co/pJLdKeRYzw:

01 • https://t.co/W6zaUtLhU0
02 • https://t.co/Eqh45LQLDz
03 • https://t.co/wWf8aolgE1
04 • https://t.co/UBMxPrpz5w

[Aquaduck @aquaduckai]

Come on in the water’s warm

https://t.co/uVSURRayhS 🌊🦆

[Daniel R. Dafoe @danieldafoe]

Everyone's excited about @darkbloomai so let's talk about distributed AI. Since launching Aquaduck AI beta yesterday, P50 tok/s for top 3 models:

1. Gemma 26B A4B -> 66 tps (33tps on DB)
2. GLM 4.7 Flash -> 53 tps (not on DB)
3. Qwen 3.8 27B -> 17 tps (not on DB)

All powered by consumer hardware!

We were one of the first 20 devices on Darkbloom back in April, but we started @aquaduckai around the same time because we wanted more device inclusivity, speed, and model dynamism.

Love what DB is exploring and imagine our implementations will be very complementary. We optimize for different goals, like making use of every computer, not just the extremely capable ones. I think we'll be two meaningful projects for distributed and local AI.

If you're interested in trying out another implementation, set up your own mini AI cloud of compute or use our public one: https://t.co/ob1wE1UKDa

[Daniel R. Dafoe @danieldafoe]

Everyone's excited about @darkbloomai so let's talk about distributed AI. Since launching Aquaduck AI beta yesterday, P50 tok/s for top 3 models:

1. Gemma 26B A4B -> 66 tps (33tps on DB)
2. GLM 4.7 Flash -> 53 tps (not on DB)
3. Qwen 3.8 27B -> 17 tps (not on DB)

All powered by consumer hardware!

We were one of the first 20 devices on Darkbloom back in April, but we started @aquaduckai around the same time because we wanted more device inclusivity, speed, and model dynamism.

Love what DB is exploring and imagine our implementations will be very complementary. We optimize for different goals, like making use of every computer, not just the extremely capable ones. I think we'll be two meaningful projects for distributed and local AI.

If you're interested in trying out another implementation, set up your own mini AI cloud of compute or use our public one: https://t.co/ob1wE1UKDa