Hugging Face

TurboQuant CUDA for llama.cpp: 3.5x KV cache compression that BEATS q8_0 quality (-1.17% PPL) 99.6% prefill speed, 97.5% decode 128K context on RTX 3090 24GB, Q6 Qwen3.5 27B github.com/spiritbuun/lla…

Qwen3.5-35B compressed 20% with 1%~ performance drop on average. Now you can fit this (4bits) with full context on 24GB of VRAM 700$~ or 1x 3090 huggingface.co/0xSero/Qwen-3.…

Next steps: - enable the 50,000 models available in inference providers - enable the 3,000,000 models available on HF - local free fast inference with llama.cpp - train and bring your own model! We don't want a world where you're forced to choose between two or three lookalike models with the same biases, limitations, forced to pay fortunes in tokens even for small tasks and send all your data to the cloud. We want a world where you have real model choice, options and freedom for your agents. Cloud, local, small, big, specialized, general, English or French, fast or slow, from six months ago or from six seconds ago, from third party or your own! Let's go!

Automate your workflow. Watch this agent bridge @github, @huggingface, and @NotionHQ to scan for models and draft research briefings in a single run. 60 lines of code for a lot of value → goo.gle/4lVDcQo

We’re releasing SAM 3.1: a drop-in update to SAM 3 that introduces object multiplexing to significantly improve video processing efficiency without sacrificing accuracy. We’re sharing this update with the community to help make high-performance applications feasible on smaller, more accessible hardware. 🔗 Model Checkpoint: go.meta.me/8dd321 🔗 Codebase: go.meta.me/b0a9fb

Been really cool to see the traction of @NousResearch Hermes Agent, the open source agent that grows with you! Hermes Agent is open-source and remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access. Starting today, you can use a bunch of @huggingface open-source models thanks to our inference provider partners. Let's go open agents!

thats it, thats the tweet huggingface.co/unsloth/Qwen3.…

People of pi. How do we feel about this?

We need more open agent traces datasets. Who can help?

@cohere just released the best speech->text model :) It currently ranks #1 for accuracy on @huggingface Open ASR Leaderboard, setting a new benchmark for real-world transcription performance. Read more 👇

🚀 Unitree open-sources UnifoLM-WBT-Dataset — a high-quality real-world humanoid robot whole-body teleoperation (WBT) dataset for open environments. 🥳Publicly available since March 5, 2026, the dataset will continue to receive high-frequency rolling updates. It aims to establish the most comprehensive real-world humanoid robot dataset in terms of scenario coverage, task complexity, and manipulation diversity. 👉 Explore the dataset here: huggingface.co/collections/un…

Model weights are here: huggingface.co/chromadb/conte…!

Introducing: Cohere Transcribe – a new state-of-the-art in open source speech recognition.

Great to see you man :) @huggingface has done so much for the open source community. Yall have been a mainstay of my life since you launched.

Wise words from @eoghan @intercom. That’s why open-source AI is so important! “We believe that the winners in such spaces must and will become full stack AI companies. And we’ve already seen this just last week with Cursor making the first such move, with Fin being the second. As features become ~free to build, the technology factors that will differentiate the players will be the AI under the hood, and if you’re using the same general purpose off-the-shelf model as everyone else, you have no durable differentiation.”

Cohere has released an Apache 2.0 model on @huggingface. No restricted license. No "research only." Actually open. Respect. Is this a one-off or a direction change for Cohere?

So cool!! I'm running @nvidia's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of @openclaw that lets you restrict the files and networks your lobster can access. I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second! The future might be local :)

After @Pinterest @Airbnb @NotionHQ @cursor_ai, today it’s @eoghan @intercom publicly sharing that they’re finding it better, cheaper, faster to use and train open models themselves rather than use APIs for many tasks. And hundreds of other companies are doing the same without sharing. Ultimately, I believe the majority of AI workflows will be in-house based on open-source (vs API). It took much more time than we anticipated but it’s happening now!

New Voxtral-4B-TTS is beautiful 💛 it sounds so good that it's whispering at closed models: "your time is over" - Demo available on Hugging Face ⬇️

I got no other than the Godmother of AI @drfeifei as a coworker at the @huggingface Miami office today! So inspiring! huggingface.co/drfeifei