My LLM command-line tool and Python library now has support for tool calling! You can define tools as Python functions or bundle them in plugins, and LLM can then make them available to models. OpenAI, Anthropic, Gemini and Ollama are supported so far. simonwillison.net/2025/May/27/ll…

Today, MiMo can see We release MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks,

Video-XL-2 🔥 long video understanding model by BAAI and Shanghai Jiao Tong University huggingface.co/BAAI/Video-XL-2 ✨ Apache 2.0 ✨ Handles up to 10,000+ frames on a single GPU ✨ 2048-frame encoding in just 12s ✨ Efficient Chunk-based Prefilling & Bi-granularity KV decoding

3 months ago, Stanford's Hazy Research lab introduced Minions, a project that connects Ollama to frontier cloud models to reduce cloud costs by 5-30x while achieving 98% of frontier model accuracy. Secure Minion turns an H100 into a secure enclave, where all memory and

Past week was insanely packed for open AI! 😱 Luckily we picked some highlights for you ❤️ lfg! 💬 LLMs/VLMs > Deepseek 🐳 released DeepSeek-R1-0528, 38B model, only 0.2 and 1.4 points behind o3 in AIME 24/25 🤯 they also released an 8B distilled version based on Qwen3 (OS) >

stop building parser pipelines 👋🏻 there's a new document parser that is small, fast, Apache 2.0 licensed and is better than all the other ones! 😱 MonkeyOCR is a 3B model that can parse everything (charts, formules, tables etc) in a document 🤠

we're all sleeping on this OCR model 🔥 dots.ocr is a new 3B model with sota performance, support for 100 languages & allowing commercial use! 🤯 single e2e model to extract image, convert tables, formula, and more into markdown 📝

Chinese instagram (RedNote) silently dropping the best VLM for general purpose OCR in just 1.7B size wasn't on my wish list 🎅

All the details of OpenAI's new base model courtesy of HuggingFace update log. - Looks like NO base model (despite their oss model cookbook page saying it is) - 21B and 117B Total Param, 3.6B and 5.1B Active MoE Model sizes - Reasoning and Agentic capabilities - License: APACHE

The OpenAI open weight models just dropped - a 20B and a 120B, both under a proper open source Apache 2.0 license!

We are releasing NuMarkdown-8B-Thinking, an open-source (MIT License) reasoning OCR model 🧠✨📄 NuMarkdown-8B-Thinking is apparently the first (!) reasoning VLM specialized in converting PDFs/Scans/Spreadsheets into Markdown files (typically used for RAG applications). It

Introducing GLM-4.5V: a breakthrough in open-source visual reasoning GLM-4.5V delivers state-of-the-art performance among open-source models in its size class, dominating across 41 benchmarks. Built on the GLM-4.5-Air base model, GLM-4.5V inherits proven techniques from

whisper.cpp is coming to ffmpeg github.com/FFmpeg/FFmpeg/…

Google just released their smallest Gemma model ever: Gemma 3 270M! 🤯 🤏 Highly compact & efficient 🤖 Strong instruction-following capabilities 🔧 Perfect candidate for fine-tuning It's so tiny that it can even run 100% locally in your browser with Transformers.js! 🤗

Meta released DINOv3 🔥 > 12 sota image models (ConvNeXT and ViT) in various sizes, trained on web and satellite data! > use for anything: image classification to segmentation, depth or even video tracking 🤯 > day-0 support from transformers 🤗 > allows commercial use! 😍

Simon Willison > I imagine this model will be particularly fun to play with directly in a browser using transformers.js. I built a fun little bedtime story generator with it 🤗

HUGE RELEASE! Nvidia just droppped: > Granary: the largest open-source speech dataset for European languages 🗣️🇪🇺 > Canary-1b-v2: 25 languages, ASR + En↔X translation > Parakeet-tdt-0.6b-v3: SOTA multilingual ASR You can now train your ASR model to understand European

You asked for it, and we listened. MULTILINGUAL Canary v2 and Parakeet v3!! 🌏 25 European languages 🏆 SotA on Multilingual Open ASR Leaderboard 🔥 600x and 2000x faster than real-time 🕰️ Timestamps! 🗣️ Speech translation (Canary) 🃏 Granary: all data is open, train it yourself!

🚨 FFmpeg 8.0 has been released! 🚨 It has many new features and bugfixes such as APV and ProRes RAW decoding, numerous Vulkan encoders and decoders, VVC decoding features etc. We have also upgraded our project infrastructure. ffmpeg.org

🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI! ～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass! ～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding ～ Controllable