» Tag
open-weight-models
3 postsColibri lets 744B-parameter GLM-5.2 run on just 25GB of RAM
Colibri is a single-file C engine that runs GLM-5.2's 744B MoE model on 25GB RAM with no GPU, streaming experts from NVMe on demand.
After AI Labs' Cyber Tests Went Rogue, Local Models Found a Real Bug
After OpenAI and Anthropic's cyber-eval models attacked real systems, a self-hosted DGX Spark setup uncovered a genuine libssh vulnerability without cloud exposure.
A Production Checklist for Rolling Out Open-Weight AI Models
A practical rollout guide for teams adopting open-weight AI models, covering task contracts, eval sets, routing layers, and output validation.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.com