#multimodal
Multimodal: 6 AI articles covering multimodal news, analysis, and research
Articles
Welcome Le Chonk: Mistral Large 4 on Hugging Face⭐8
Mistral Large 4, nicknamed Le Chonk, is now on Hugging Face: a 1T-parameter MoE multimodal model with 52B active parameters, built for image-text-to-text tasks.
Meta Launches Open-Weight AI Model That Runs on Macs⭐8
Meta launches Muse Spark Open, a 816B-parameter open-weight AI model with a 1M token context window that runs locally on Macs.
Multimodal Open Decision Models for the Edge: LiquidAI's LFM2.5⭐8
LiquidAI's LFM2.5-Encoder-350M is a compact 0.4B multimodal encoder built for edge AI, powering fast, on-device decision models and real-time pipelines.
Meta Unveils Muse Glimmer: Local, Agentic, Multimodal, and Open Source⭐8
Meta unveils Muse Glimmer: an open-source, multimodal AI that runs locally and autonomously, now on Hugging Face for developers.
Building a Multimodal RAG Pipeline with NVIDIA NeMo Retriever,⭐8
Build a multimodal RAG pipeline using NVIDIA NeMo Retriever, hosted NIMs, LanceDB, reranking, and grounded generation. Step-by-step tutorial included.
Black Forest Labs Releases FLUX 3: A Multimodal Flow Model for⭐8
Black Forest Labs unveils FLUX 3, a multimodal flow model capable of generating images, video, audio, and predicting robot actions.