Image created with OpenAI GPT-Image-1. Image prompt: 1966 Kodachrome photo-look, thin white frame, forest-green title band in upper left with stacked yellow/white serif text reading “LOCAL”, cream goat mid-bleat, mouth open scene featuring a red map-marker pin sign attached to the fence; gentle film grain, overcast daylight
🤖 Build Local AI Agents Create intelligent AI agents running locally with LangGraph and Ollama. Transform basic chatbots into reasoning agents that make decisions, with real-time monitoring in LangGraph Studio. 🔍 Read the tutorial: https://x.com/LangChainAI/status/1931758230314623435
Bring the AI to you my friend: pip install mlx-lm”” / X https://x.com/awnihannun/status/1933266802450313715
RT @osanseviero: Gemma 3n in desktop is here! 🚀 🤗Desktop (Mac/Windows/Linux) + IoT 🔥2B and 4B 🧠Powered by new LiteRT-LM library Github: h…”” / X https://x.com/demishassabis/status/1932607299178148184
RT @mollycantillon: Everything will be local Yesterday I gave a talk about Real-World Applications of MLX and built a fast on-device seman…”” / X https://x.com/awnihannun/status/1933273566763786699
Announcing Magistral — our @MistralAI first reasoning model — excelling in domain-specific, transparent, and multilingual reasoning. https://x.com/sophiamyang/status/1932451856447586312
Announcing Magistral, our first reasoning model designed to excel in domain-specific, transparent, and multilingual reasoning. https://x.com/MistralAI/status/1932441507262259564
Magistral | Mistral AI https://mistral.ai/news/magistral
Mistral just released their reasoning models: Magistral-Small and Magistral-Medium Magistral Small is open-source and based on the 24B Mistral-Small 3.1, and can run on a single RTX 4090. Unfortunately it gets crushed by Qwen3-32B and Qwen3-30B-A3B Download Link: https://x.com/scaling01/status/1932445360380612712
Mistral really cooked – 24B, Based on Mistral Small 3.1, Multilingual, 128K context (40k effective), Apache 2.0 licensed! 🔥 Works on MLX, llama.cpp, transformers, vllm and more ⚡ https://x.com/reach_vb/status/1932449015657836730
The Mistral team at it again with Magistral! GRPO with edits: 1. Removed KL Divergence 2. Normalize by total length (Dr. GRPO style) 3. Minibatch normalization for advantages 4. Relaxing trust region Paper: https://x.com/danielhanchen/status/1932451325398413518
