Open-Source LLMs You Can Host
How to choose a hostable open-weight model based on task fit, hardware limits, governance needs, and support burden rather than hype.
Open-Source
Gravity Rewired: From Huff’s 1960s Trade Areas to a Pythonic Spatial Intelligence Stack
Location decisions are rarely about location alone. A supermarket does not win customers simply because it is nearby. A hospital does not serve a population just because it sits inside a neat administrative boundary. An airport does not own a catchment area because someone drew a circle around it in a slide deck, though many slide decks have committed worse crimes. ...
Beyond the Pull Request: What ChatGPT Teaches Us About Productivity
TL;DR for operators Most companies still ask the wrong first question about LLMs in software development: “Do they make developers write code faster?” That question is not useless. It is just too small. A recent paper by Sardar Bonabi, Sarah Bana, Vijay Gurbaxani, and Tingting Nian uses Italy’s temporary 2023 ChatGPT ban as a natural experiment to examine what happened to public GitHub activity when Italian developers abruptly lost access to ChatGPT, compared with similar developers in France and Portugal.1 The study covers 88,022 open-source software developers and looks at a 16-week window: eight weeks before the ban, four weeks during it, and four weeks after access was restored. ...
BGE Large EN v1.5
A high-quality English embedding model from BAAI, optimized for semantic search, retrieval-augmented generation (RAG), and ranking tasks.
BGE Reranker Large
A high-performance cross-encoder reranking model from BAAI designed to improve retrieval accuracy in RAG and search systems.
BLOOM
A multilingual large language model developed by the BigScience initiative, capable of generating text in 46 languages and 13 programming languages.
CLIP ViT-B/32
A widely used multimodal model from OpenAI that learns joint image–text embeddings, enabling zero-shot image classification, search, and multimodal applications.
DeepSeek-R1
An open-source reasoning model achieving state-of-the-art performance in math, code, and logic tasks.
DINOv2 ViT-L/14
A powerful self-supervised vision foundation model from Meta AI, producing high-quality image embeddings for vision tasks without task-specific labels.
FLUX.1 [dev]
A 12-billion-parameter rectified flow transformer capable of generating images from text descriptions.