unsloth.ai
Run GLM-5.2 on local hardware with Unsloth GGUFs.
Documentation for running Z.ai's GLM-5.2 locally with Unsloth Dynamic GGUFs. Covers model specs (744B params, 1M context), quantization options, and practical usage tips.
AI-generated summary based on Hacker News comments
🔗 Full discussion: https://news.ycombinator.com/item?id=48636377
AI regulatory intelligence platform 🌱 Sponsored
Tiny, pure-C engine for running GLM-5.2 on hardware.
Detect hardware and see which AI models you can run locally.
Real-time 30B parameter LLM inference on low-power hardware.
Get Local Leads with the power of AI.
On-device voice AI for macOS with local RAG - no cloud.
Supporting open, local AI with ggml, llama.cpp, and Hugging Face
Explore queries with a local Llama model
Documentation on hardware anti-rollback incidents.
Open-source router firmware for open hardware
First 27B-class model that runs on a phone with multimodal reason
Open-source AI coding assistant with a local server.
Generate hands-on, multi-part tutorials with LLM-tuned skills
Real-time flight tracking on a 3D globe with 10k+ flights.
Run Python in your browser with no install or sign-up.
No comments yet. Have you tried it?