Colibrì Runs a 744-Billion-Parameter GLM-5.2 Model on 25 GB of RAM
A developer has managed to run GLM-5.2, a mixture-of-experts model with roughly 744 billion parameters, on a consumer computer with around 25 GB of RAM and no graphics card. The
Category: Databases
Tabularis wants to become the database client AI agents can actually use
DBeaver has held a very comfortable place for years in the daily workflow of many developers, system administrators and data teams. It is complete, free in its Community edition, cross-platform
LEANN claims 97% smaller RAG indexes and could make local AI far more practical
One of the biggest hidden costs in retrieval-augmented generation is not the model itself, but the storage burden of the vector index sitting underneath it. That is the problem LEANN
PocketBase Gains Ground as an Open Source Backend Alternative to Firebase and Supabase
The market for backend services for web and mobile apps has long been dominated by a small group of familiar names, especially Firebase and, more recently, Supabase. But alongside those
MariaDB moves to buy GridGain to speed up real-time AI workloads
MariaDB has signed a definitive agreement to acquire GridGain Systems, the company best known for its in-memory computing technology and for being the original creator of the open-source Apache Ignite
Google Wants to Fix Text-to-SQL for Real: MCP Toolbox for Databases Targets Production, Not Demos
Over the past two years, “GenAI text-to-SQL” became one of the most repeated promises in enterprise AI: describe your question in plain English and get perfect SQL, ready for production.
Scaling SQL in Production: Practical Lessons for Sysadmins When the “Monolith” Isn’t the Problem
For years, plenty of architecture discussions have leaned on a convenient idea: that SQL databases “don’t scale,” and that beyond a certain size the natural move is to abandon the
OpenAI’s “boring” PostgreSQL scaling story: one primary, 50 read replicas, and a long list of guardrails
At a time when “scale” is often synonymous with sharding everything and building increasingly complex distributed systems, OpenAI is describing a notably restrained database architecture behind ChatGPT: a single PostgreSQL
Databasus: a self-hosted database backup manager that finally feels built for sysadmins
Every sysadmin has seen the same pattern: backups start out as a clean pg_dump job, a couple of cron entries, and a bucket. Six months later it’s a fragile web
sqlit, the “lazygit” for databases: a terminal UI to run SQL queries without firing up a heavyweight desktop app
For years, running a couple of database queries has come with a hard-to-defend paradox: to do something simple, many developers end up launching heavy apps, installing huge toolchains, burning memory,
You might be interested in...
