- TurboFieldfare (Part 1): Run 26B LLM in 2GB RAM
Explore TurboFieldfare, an engine streaming Gemma 4 26B-A4B experts on-demand from SSD on Apple Silicon with ~2GB RAM.
2 min🇺🇸 English - TurboFieldfare (Part 2): Swift & Metal Runtime Optimization
Deep dive into Swift 6.2 and Metal Compute Shaders enabling LFU caching and SSD latency reduction in TurboFieldfare.
2 min🇺🇸 English - TurboFieldfare (Part 3): CLI, Mac App & OpenAI Server
Set up CLI tools, native Mac application, and local OpenAI API server for TurboFieldfare along with performance benchmarks.
2 min🇺🇸 English - TurboFieldfare Series Overview: Run 26B LLM in 2GB RAM
Complete guide index to the TurboFieldfare series covering SSD expert streaming architecture, Metal runtime optimizations, and local API server setup.
1 min🇺🇸 English - World Models: Learning Environment Models with PyTorch
An in-depth guide to Ha & Schmidhubers World Models architecture implemented in PyTorch by nik-55 (VAE, MDN-RNN, Controller).
3 min🇺🇸 English - Chrome DevTools MCP — AI Agents with Browser Debugging
Official Chrome DevTools MCP server gives AI agents full browser debugging — inspect DOM, console, network, performance, memory, and Lighthouse.
4 min🇺🇸 English - Gortex — Code-Intelligence Engine for AI Agents
Gortex is a high-performance graph-based code-intelligence engine that cuts AI agent token usage up to 50× with 257-language support.
4 min🇺🇸 English - Graphify — Knowledge Graph for AI Coding Assistants
Graphify maps entire codebases into queryable knowledge graphs using tree-sitter AST parsing, saving AI agents from reading raw files.
4 min🇺🇸 English
Back
Blog
🇺🇸EnglishShowing 8 of 203 postsView all by year →