Tag: local-llm
-
Local LLMs with Ollama: RAG over internal docs without handing them to a third party
A field-tested take on RAG over internal docs without handing them to a third party with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Caching embeddings locally for a private retrieval layer
Running retrieval against a local Ollama embedding model is easy. Not re-embedding the same document twice, and never letting anything sensitive touch an external API, is the part worth getting right. A local cache and a content hash do most of the work.
-
The Complete Mac AI Setup, 2026 Edition — Everything in One Guide
The complete guide to a Mac AI setup in 2026 — Ollama, Whisper, MLX, RAG, and local LLMs organized into four tiers by cost and time, with a RAM-to-model hardware table and honest guidance on when to stop upgrading.
-
What 100 Days of Daily Local AI Use Taught Me About the Hype
100 days of daily local AI use on Apple Silicon, audited honestly — what stuck, what got abandoned, real productivity numbers vs the 10x hype, and the durable lessons about local LLMs, Whisper, and workflow design.
-
Local LLMs with Ollama: When a local 7B beats a cloud 70B in latency-sensitive loops
A field-tested take on when a local 7B beats a cloud 70B in latency-sensitive loops with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
The Multi-Mac AI Cluster — Insane Overkill or the Future?
Can you build an AI cluster from multiple Macs? A hands-on look at exo distributed inference on Apple Silicon, Thunderbolt bridge performance, real token-per-second numbers, and when a Mac cluster beats one big Mac Studio.
-
Why I Downgraded From the Biggest AI Model — and Got Better Results
The contrarian case for small local LLMs on Apple Silicon. Why downgrading from a 70B to an 8-14B model improved real productivity through latency, iteration speed, and prompt discipline — plus the escalation rule for when big models still win.
-
The Backup Strategy for People With 500GB of AI Models
Storage and backup strategy for local AI model hoarders: deduplicating Ollama, LM Studio, and Hugging Face caches, Time Machine exclusions for model blobs, external SSD symlinking, and what actually deserves a backup.
-
Local AI for Students — The Study System That Beats Tutoring
A complete local AI study system for students: refurbished M1 MacBook with Ollama, Whisper lecture transcription, Feynman-technique prompts, Anki flashcard generation, and an honest take on AI vs human tutoring and academic integrity.
-
I Tracked Every AI Query for a Month — The Results Changed My Setup
I logged every AI query for 30 days using Open WebUI logs and the llm CLI. The data showed 80% of queries run fine on a local model — here's the routing setup and cost savings that followed.
-
Local LLMs with Ollama: Thermal budget of a MacBook pretending to be a server
A field-tested take on the thermal budget of a MacBook pretending to be a server with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
The Spreadsheet Killer — Local AI Data Analysis on Your Mac
Natural-language data analysis with local LLMs on Apple Silicon. Why LLMs should write pandas code instead of doing math, a local code-interpreter setup with Ollama and Jupyter, and prompt patterns for analyzing bank CSV exports privately.
