Search: “clem-delangue--x”

llama.cpp adds MTP for the Qwen3.6 family This is a significant milestone for the local AI ecosystem. The performance jump with these changes is massive and elevates local inference on commodity hardw

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀 Qwen3.6-27B dense generation (on A10G): From 25 tok/s → 45 tok/s (+78%). Two flags on llama-server: --spec-type draf

Clem Delangue reports that his follower count on X (formerly Twitter) is growing faster than on other social media platforms, and credits @nikitabier and their team for this success. The post suggests

okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi

Reachy, a humanoid robot, participated in a rap battle event at an AI engineer community gathering in Singapore. The event was hosted or documented by Clem Delangue, co-founder of Hugging Face, sugges

Releasing my first kernel on @huggingface: MaxSim Late-interaction retrieval (ColBERT / PyLate) bottlenecks on materializing the full similarity matrix. This kernel avoids it by using tiled scoring wi

Very cool to see Cursor doubling down on training great models. In my opinion, ultimately all serious companies in AI will want to train models themselves, based on open-source instead of outsourcing

We causally trained a lot of SOTA search models internally, shall we make some small release from time to time 🤣🤣 @bo_wangbo stealth releasing probably the strongest open multilingual ColBERT (and it'

'We give you model choice, without infrastructure chaos' — @MichaelDell, live from #DellTechWorld 🎤 Kimi K2.6, DeepSeek V4 Pro, GLM 5.1, MiniMax M2.7 & DeepSeek V4 Flash are now one click away on Dell

A new @bgurley blog post! I have been thinking about how sophisticated executives are using open source in super creative ways. Started writing this three years ago. Excited to finish it up and publis

AI teams shouldn’t have to choose between expensive object storage and painful git workflows. @huggingface Storage is built for model weights, datasets, checkpoints and artifacts: - simple per-TB pric

Open-ended coding training data may no longer be the bottleneck: AI can scale open-ended tasks—and even outperform human-expert curation. FrontierCS team is releasing FrontierSmith: a system for synth

Paper of the day! https://huggingface.co/papers/2605.13301 We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and

Clem Delangue expresses optimism about the role of American open source AI development within the broader AI ecosystem, highlighting the significant experimentation and creative innovation occurring i

Very thoughtful post on the role and success of open source, including potential applications for AVs and AI. Long, but worth the read. -- 'Open source is no longer just how good software gets built.

We’re releasing a 30B-A3B reasoning model that reaches gold-medal level across both physics and math Olympiad evaluations: IPhO directly, and IMO/USAMO with test-time self-verification and refinement.

Are scaling laws finally working for time series foundation models? Today, @datadoghq is releasing Toto 2.0 weights in Apache 2.0 on @huggingface. It's a family of open-weights TSFMs from 4M to 2.5B p

Portable Reachy Mini is likely a compact, mobile robotic arm or manipulation device, with this post from Hugging Face's CEO Clem Delangue presumably announcing or promoting its availability or readine

SWE-ZERO and AgentTrove are trending datasets on Hugging Face related to software engineering and agentic AI systems. The post indicates growing interest in trace datasets that capture agent behaviors

A utility tool was created to streamline sharing GPU profile traces by uploading them to Hugging Face buckets using the command `uvx trace-tuil -b `. This simplifies the process of distributing perfor

Toto 2.0 is here: Datadog AI's 5 open-weights forecasting models (4m-2.5B params) finally make scaling work for time series forecasting! #1 on BOOM, GIFT-Eval, and TIME. Weights/code Apache 2.0. 🔗 Rea

As President Trump meets President Xi this week, a call to the American AI community: If your startup, lab, non-profit or company benefits from open international AI - especially Chinese (Deepseek, Qw

Asymmetry of capabilities is when there is great risk. Diffusion of capabilities maintains an adversarial equilibrium and stability. Don't let the fear-mongerers win. We asked the CEO of HuggingFace @

Co-sign. We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. 'Six, seven years ago, at

Good catch @theojaffee 😂 Media We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. 'Si

Introducing SWE-ZERO-12M-trajectories: the largest agentic trace dataset in the open, 5.7x larger than the previous largest. 112B tokens · 12M trajectories · 122K PRs · 3K repos · 16 languages https:/

This post discusses how local AI deployment could address growing energy consumption and cloud computing capacity constraints as demand for AI infrastructure increases. The author, Hugging Face CEO Cl

Hugging Face announced the Reachy Mini, likely a smaller or more affordable version of the Reachy robotic arm platform. The announcement suggests a product launch or release becoming available, potent

Poolside is hosting a 2-day model research hackathon in London. Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intell

We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. 'Six, seven years ago, at the time

After seeing the new OpenAI and Thinking Machines voice APIs, I did finally order a Reachy. Way more excited to talk to this thing than a Google puck Reachy is mad, but RAM costs + tariffs are forcing

Clem Delangue of Hugging Face expresses satisfaction with their AI product, highlighting a personal moment where his child interacted with it as a meaningful validation of the investment. The post sug

@ivanfioravanti @Prince_Canuma @huggingface this is a fully local stack to get your Reachy Mini running (with vision/tts/stt) on a mac. Uses mlx-vlm, mlx-audio, gemma4 It contains some examples to run

Just ordered Reachy! Can't wait to do some fun projects with my kids. Reachy is mad, but RAM costs + tariffs are forcing our hand. Prices will go up on June 1st! Still at the early bird price until th

Meet physics-intern🧑‍🎓, our agentic framework for theoretical physics. It takes Gemini 3.1 Pro from 17.7% to 31.4% on CritPt, a new SOTA on one of the hardest benchmarks for LLMs. Theoretical physics

Reachy is mad, but RAM costs + tariffs are forcing our hand. Prices will go up on June 1st! Still at the early bird price until then though if you were looking for an excuse to get one now: http://hf.

Clem Delangue, CEO of Hugging Face, shared excitement about seeing Reachy Mini, a small humanoid robot, featured on the cover of Linus Tech Tips' latest video. The post suggests Reachy Mini received n

Hugging Face offers substantial infrastructure capabilities for hosting machine learning models, datasets, and agent memory systems. The statement suggests that organizations currently using alternati

🚨 Today: OpenMed Agent ships in preview. Built on @huggingface: → HF endpoints power clinical extraction + terminology → MCP for your own services → Every tool call, every plan, fully visible 1,000+ O

We just crossed 1,000,000 public datasets on Hugging Face! That's petabytes of data available that millions of AI builders are downloading, analyzing, and training AI models on every day! What's inter

We've just hit 1M open datasets on the Hugging Face Hub 🎉 Open models need open data. Today we hit that milestone, together with the most incredible community in AI! 🤗 Onwards to the next million 🚀 Me

3 weeks since ml-intern launched and we just hit 1M messages exchanged. that's 3.3 agent-years of ML research in 21 days. 2 months worth of research every day. 17,383 training jobs total. talk about A

Finding Hugging Face Buckets really, really useful - very easy to mount & write to Probably easiest sort of bucket I've worked with so far, DX is much better than S3, R2, modal, etc. @huggingface team

🆕 Hugging Face 🤝 Hermes Agent 🔥 > we added Hermes Agent to local apps: run it locally with any compatible GGUF/MLX model > shipped native traces support for Hermes Agent: visualize your Hermes traces

I have a new job! Excited to announce that I will be working with Hugging Face to make local models work great in OpenClaw and other open agent harnesses! I will be building in public and documenting

🤯 i need all of you to stop what you're doing and look at this @webassembly + transformers.js + @googlegemma powered robot, running completely offline I think Reachy is the one who needs chess lessons