I've uploaded Q4, Q8 and BF16 MTP draft models in their own repo It should work natively with yesterday's llama.cpp merge huggingface.co/notSnix/Step-…

Dostlar çok güzel bir haberim var. Yakında sağolsun @ASUSTR 'nin desteği ile Asus'un ExpertCenter Pro ET900N G3 Desktop AI Supercomputers'ını birkaç günlüğüne uzaktan bağlanıp test edeceğim. Makine'de Nvidia'nın GB300 Grace Blackwell Ultra yer alıyor. 748GB Coherent Memory yer alıyor. Ama en efsanesi GB300'ün sahip olduğu 252GB HBM3e (7.1 TB/s) VRAM aslında 🔥 Özellikle @MiniMax_AI M3, @Zai_org GLM 5.1, @Kimi_Moonshot K2.7-Code, @Alibaba_Qwen 3.5-397B, @deepseek_ai v4 Flash gibi modelleri NVFP4 ile oldukça zorlayacağım; 50-100 paralell istek performansı, Agentic paralel 5-10 araçla kullanım performansı gibi.

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

GLM-5.2 is Fully Open, Frontier Intelligence Belongs to Everyone Today, the sudden restriction of certain frontier models is deeply regrettable. At a time when access to frontier models is abruptly cut off for non-technical reasons, we are even more convinced of one thing: science should be global. The path to AGI (Artificial General Intelligence) must never be enclosed by high walls. We have always believed that AGI should be the cornerstone for all of humanity to collaboratively explore the boundaries of intelligence and solve complex challenges, rather than a privilege monopolized by a few rules and subject to revocation at any moment. In the face of external blockades and restrictions, our attitude is one of radical openness. Frontier intelligence must remain open-source, accessible, and buildable, serving every dedicated developer. GLM-5.2 is Zhipu's most capable open-source model to date. It not only supports a truly usable 1M context window but also maintains a continuous lead in the independent completion of long-horizon tasks, providing solid foundational support for building complex agent applications. It also continues to be our main engine for creating the strongest domestic coding model. Tonight at 5:21—at this special moment—GLM-5.2 will officially be available to all GLM Coding Plan users (including Lite / Pro / Max). The API will also go live next week. A step closer to frontier intelligence for everyone. The future of AI is open, and it is for the people. ModelKey: GLM-5.2

Damn so many model releases GLM-5.2 is here

What

Fable 5 is very good at disassembling

Fable 5 is actually usable in @droid

oh nice Free Codex limit resets

MiniMax M3, Open-Weight, Now On Hugging Face , with only ~428B parameters and ~23B activated parameters Weights: huggingface.co/MiniMaxAI/Min… MiniMax Sparse Attention: huggingface.co/papers/2606.1…

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: 21.8% on Kimi Code Bench v2, 11.0% on Program Bench, and 31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6. 🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates. ⚡️ 6x High-Speed Mode coming soon! 🔌 Available today via Kimi API and Kimi Code. 🔗 Kimi Code: kimi.com/code 🔗 API: platform.moonshot.ai

DiffusionGemma 26B A4B NVFP4 on RTX Pro 6000 Decode: 852 tok/s Prefill peak: >50,000 tok/s Diffusion models is the future, I want more

Are we fucking serious…

lets see what this macOS 27 update is all about

Downloading right now - Q4 for single 3090 - Q8 for TP=2 on dual 3090 - BF16 for RTX Pro 6000 Lets see how fast they are⚡

Enough fans for the summer?

Hell yeah We got fans

The speed on diffusion models is insane

This is going to be fun to play with

HAHAHAHAHAHHAHAH