Tag: local-llm
All the articles with the tag "local-llm".
- AI Tools & Benchmarks
We Ran Three Local Models Through 23 Hidden JavaScript Tests
A reproducible Ollama benchmark compares code correctness, generation speed, model size, and measured cost on an Apple M2 Max.
- AI & Games
NVIDIA ACE Unreal Engine 5 Guide: On-Device AI NPC Architecture
Updated:How NVIDIA ACE connects local LLMs, speech, RAG, tools, and Unreal Engine 5 to build lower-latency AI NPCs, plus the production tradeoffs.
- AI Engineering
Bonsai 27B Runs on an iPhone: The Case for Emergency and Hybrid AI
PrismML compressed a 27B model to 3.9GB. Its strongest use may be a private assistant that keeps working when connectivity disappears.
- AI & Games
AI NPC Architecture Guide: Build Characters Without Losing Game Control
A production architecture for AI-native game characters covering state, RAG, local models, latency, policy, deterministic actions, testing, and cost.
- AI & Games
AI Society Lets 25 Local LLM Characters Build a Civilization on Your PC
Updated:AI Society runs autonomous character dialogue, relationships, work, and decisions through Ollama or LM Studio without a cloud subscription.
- AI & Games
The Moment of Panic Runs Unreliable AI Advisors Locally on Your Gaming PC
Updated:The Moment of Panic turns a local open-source LLM into biased strategic advisors while deterministic game logic controls truth and consequences.