WebsiteHunt is broughtBrought to you by Redact Everything
CG
Colibri: GLM-5.2 on 25GB RAM
Tiny, pure-C engine for running GLM-5.2 on hardware.
Run GLM-5.2 (744B MoE) on a consumer machine with ~25 GB RAM using pure C and zero dependencies. Experts are streamed from disk, enabling a tiny engine with a massive model. No BLAS, no Python at runtime; optional CUDA tier for pinned experts.
Discussion highlights
AI-generated summary based on Hacker News comments
🔗 Full discussion: https://news.ycombinator.com/item?id=48842459
Comments
Loading comments...
Category
You might also like
ProjectManagementTools
Optimize your Projects with ProjectManagementTools 🌱 Sponsored
Labrynth AI
AI regulatory intelligence platform 🌱 Sponsored
GLM-5.2 Run Locally
Run GLM-5.2 on local hardware with Unsloth GGUFs.
Lessons Learned Shipping 500 Units
Building hardware as a software engineer, sharing it.
Lamini
LLM engine for rapidly customizing models
OO
OpenWrt One
Open-source router firmware for open hardware
FO
Flipper One Tech Specs
Hardware and software specifications for Flipper One.
Eraser 2.0
The whiteboard for engineering teams
Q3
Qwen3-30B for Raspberry Pi
Real-time 30B parameter LLM inference on low-power hardware.
Hello
The best search engine for software developers
Trieve HN Discovery
Open source search engine for Hacker News
SignalProcessingJobs.com
The #1 Job Board for Signal Processing Engineers
PasteJustit.com
for sharing and managing text online
Comb.io
The search engine for TV shows.
GS
Get Shit Done
Meta-prompting and context engineering for Claude Code.
Laurent Le Brun's Blog
Reflections on developer tools and software engineering.
KE
Keyer
Firmware and goodies for a one-handed chorded keyboard.
Squad Central
Smarter tools for software resource planning.
Rewind
The search engine for your life
PE
Prompt Engineering Interactive Tutorial
Learn to engineer optimal prompts for Claude AI.
StratChat Premium
An AI-driven search engine for stocks, and investing