gabs

[gabs @gabsprogrammer]

https://t.co/JVp1iYKzLI

[gabs @gabsprogrammer]

@Matthewrogers What would Thor ARM64 be?

[gabs @gabsprogrammer]

@OpenAI This looks more like an episode of Black Mirror.

[Google Gemma @googlegemma]

Meet Gemma 4 12B!

A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.

Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

[gabs @gabsprogrammer]

@PapaHardware 9070 xt inexistente nessa lista?

[gabs @gabsprogrammer]

@thayto_dev ``Claude, leia o arquivo agents.md dentro do projeto``, isso não é suficiente? kkkkkk, claro q vai funcionar

[Ahmad @TheAhmadOsman]

14x RTX 3090s + Qwen 3.6 27B

Running 42 agents IN PARALLEL at full 256k context

- exl3 6bpw
- fp8 KV Cache
- Aphrodite Inference Engine w/ tp=2, pp=7

The world of agents will run locally btw

[gabs @gabsprogrammer]

@tekwendell @asrock Yes, I bet they cost $6k +

[gabs @gabsprogrammer]

@TeksEdge 🤔🤔

[njdeprê - marlon @njdmarlon]

Neymar via instagram.

The last dance. 🙏🏾🇧🇷

Vamos buscar

[gabs @gabsprogrammer]

@nvidianewsroom wow

[NVIDIA AI @NVIDIAAI]

Introducing Cosmos 3: Our latest frontier model for Physical AI

Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation.

Today we’re releasing Super (32B) and Nano (8B) variants.

[X Freeze @XFreeze]

Entire world: We need more GPUs

Meanwhile, Jensen Huang:

[gabs @gabsprogrammer]

@The_Only_Signal @AMD Congratssss!!!!

[Mike Bradley @The_Only_Signal]

Just won a shiny new Strix Halo laptop in the @AMD Lemonade SDK Developers Contest, and so can you! Just head over to Lemonade SDK’s Discord and they’ll get you all sorted out. The criteria is SUPER simple. Build cool stuff on AMD hardware and submit it. Have fun, and if you can’t BUY a GPU, you can always WIN ONE!!! Enjoy!!

https://t.co/0psKF0kcG4

[Mike Bradley @The_Only_Signal]

Someone out there likely needs this:

[Mike Bradley @The_Only_Signal]

Someone out there likely needs to see this:

M4 Mac Mini, 120 GB/s
AMD Strix Halo, 256 GB/s
Nvidia DGX Spark, 273 GB/s
M5 32 Core MacBook Pro, 460 GB/s
Intel Arc Pro B70 GPU, 608 GB/s
M5 40 Core MacBook Pro, 614 GB/s
Nvidia RTX 3090 GPU, 936 GB/s
Nvidia RTX 5090 GPU, 1,792 GB/s

[gabs @gabsprogrammer]

@joaomviso caso queira conhecer > https://t.co/cq0x2GJNde um projeto que eu participo ;)

[Mike Bradley @The_Only_Signal]

Setup Step 3.7 Flash on two Blackwell RTX PRO 6000 GPUs and got it running and recorded the configs as well as early data like tokens per second on basic inference. Running extended bench tests now just wanted to get this to folks early.

https://t.co/9yeoVrIlDR

[gabs @gabsprogrammer]

@The_Only_Signal This is https://t.co/fSB21ZfsXd 😎

[Mike Bradley @The_Only_Signal]

Going from machine in a box, to chatting with a local Hermes Agent on your phone in under ten minutes with our new Dream Server feature. The phone portal is cool for single user, but you could also use this as a service or hardware business to ship pre configured agent nodes.