Tag: local-llm
Page 2 of 7 • 71 posts total
-
Local LLMs with Ollama: Running evals locally before trusting a new model
A field-tested take on running evals locally before trusting a new model with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
What's Coming Next for AI on Mac — and How to Be Ready
Where on-device AI on Apple Silicon is heading: shrinking open models, rising memory bandwidth, Apple's Foundation Models framework, agentic AI, and local multimodality. Practical advice on hardware, skills, and the local AI stack to be ready.
-
The 7 AI Mistakes Mac Power Users Keep Making
Seven common local LLM mistakes on Mac and how to fix them. Covers Ollama context length, quantization tradeoffs, VRAM limits on Apple Silicon, swap death spirals, Modelfiles, and hybrid cloud-local routing with exact commands.
-
I Connected AI to My Smart Home Through a Mac Studio
How to connect a local LLM to Home Assistant and HomeKit using a Mac Studio as an always-on smart home brain. Fully local voice pipeline with Whisper, context-aware automations, latency versus Siri and Alexa, and honest setup complexity.
-
The AI Email Workflow That Saves Me 5 Hours Every Week
A realistic AI email workflow on Mac using Apple Mail, Shortcuts, and a local LLM. Includes a reusable personal style prompt, templates for the four most common reply types, and an honest hour-by-hour breakdown of the time saved.
-
Why Every Writer Needs a Local LLM (and How to Set One Up)
How writers can use a local LLM on Mac for manuscript feedback, line editing, and research summarization. Ollama setup guide for non-technical writers, model recommendations, and two ready-to-use editor system prompts.
-
The M-Series Chip Buying Guide for AI — What Actually Matters
Which Mac to buy for local AI and LLMs — M-series memory bandwidth compared (base vs Pro vs Max vs Ultra in GB/s), RAM tiers mapped to model sizes from 8B to 70B+, why the Neural Engine barely matters, and buying advice for students, developers, and AI homelabs.
-
Local AI Translation Beats Google Translate — and It's Private
How to run private, context-aware AI translation locally on a Mac with Ollama and Apple's offline Translate app. Czech-English quality comparison vs Google Translate, a system-wide Raycast translate hotkey, and document translation that preserves formatting.
-
RAG on Your Own Notes — Build a Second Brain That Actually Answers
How to build local RAG over your personal notes on a Mac — Obsidian with a community AI plugin and Ollama, AnythingLLM, and Open WebUI compared, plus chunking, embedding models, and honest limits.
-
Local LLMs with Ollama: Pairing Ollama with Continue or Cline for a private IDE
A field-tested take on pairing Ollama with Continue or Cline for a private IDE with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Your Mac Studio Can Replace a $1,500/Month AI API Bill
When does a Mac Studio running local LLMs beat paying OpenAI or Anthropic per token? Break-even math, latency benchmarks, Ollama and MLX server setups, and the hybrid pattern for indie developers.
