Category: AI Research

This category contains 44 pages.

• Agentic Tool-Use Loops
• AI Chat
• AI Tips and Tricks with Ollama
• bf16 LoRA vs 4-bit QLoRA
• Browser LLMs
• Building an MCP Server
• Building MCP Servers as systemd User Services
• Building MCP Tools for a Local LLM
• Choosing a Local LLM
• Converting HF Models to GGUF with llama.cpp
• Coqui TTS Setup Guide
• Custom Wake Word with openWakeWord
• Does Distillation Add Knowledge or Just Style?
• Evaluating a Fine-Tuned Model
• Evaluating LLMs with Local Benchmarks
• Fine-Tuning with Unsloth
• GGUF Quantization Tiers Compared
• Jetson Orin as an Ollama Host
• Jetson Orin Nano SDK Manager CLI Flashing
• Knowledge Distillation Lab (theLAB Genesis)
• Knowledge Distillation, End to End
• Linux Swap Memory Guide
• Local Image Generation with ComfyUI
• MediaPipe Hands
• Ollama AI Cheat Sheet
• Ollama Cloud vs Local: Model Routing on the Fleet
• Ollama Custom Model Creation
• Ollama Parameters Guide
• OmniVoice TTS Setup
• Parakeet ASR Setup
• Picking a Teacher Model
• Pooling VRAM Across Two GPUs for a 32B Model
• Prompt Engineering Patterns
• Qwen3.5 GGUF to Ollama Conversion Gotchas
• RAG with Local Embeddings
• Serving Multiple Models on a Dual-GPU Box
• Speculative Decoding
• Temperature & Sampling: Determinism vs Creativity
• The AI Council
• The Fully-Local Voice Stack
• Tool Calling & Structured Outputs with Local Models
• Vector Databases for Local AI
• vLLM vs Ollama vs llama.cpp
• Whisper with Timestamps