Tag: local-llm
Page 3 of 7 • 71 posts total
-
Fine-Tune Your Own AI Model on a MacBook — Yes, Really
Step-by-step LoRA fine-tuning with MLX on a MacBook — preparing a JSONL dataset, mlx_lm.lora flags, training times on M-series chips, evaluating results, and serving the fused model with Ollama.
-
Apple Intelligence vs. Local LLMs — What Apple Doesn't Tell You
An honest comparison of Apple Intelligence and self-hosted local LLMs on Mac. What runs on-device vs Private Cloud Compute, the 3B model's hard limits, and when to run your own models with Ollama instead.
-
I Built a Private ChatGPT for My Family on a Mac Mini
How to build a private family ChatGPT alternative with Ollama and Open WebUI on a Mac Mini. Multi-user accounts, iPhone access, Tailscale remote access, and real power consumption numbers.
-
The 128GB Mac Studio Trick AI Researchers Don't Want You to Know
Running 70B parameter LLMs at home on a 128GB Mac Studio. Quantization explained, GGUF versus MLX formats, real tokens per second on M-series Ultra, power draw versus multi-GPU rigs, and the AI homelab economics.
-
Local LLMs with Ollama: Keeping a small local model honest with tight prompts
A field-tested take on keeping a small local model honest with tight prompts with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Apple MLX Is the Most Underrated AI Framework Right Now
A practical guide to Apple MLX and mlx-lm on Apple Silicon. Why MLX beats llama.cpp for some workloads, the MLX community models on Hugging Face, and LoRA fine-tuning a local LLM on a MacBook in one afternoon.
-
The MacBook Pro Setting That Doubles Your AI Performance
How to raise the macOS GPU memory limit with sudo sysctl iogpu.wired_limit_mb to run bigger local LLMs on a MacBook Pro. Safe values per RAM tier, persistence setup, High Power Mode, and thermal tips.
-
I Replaced My $20 AI Subscriptions With One Mac Studio
Cost-benefit analysis of replacing ChatGPT-style subscriptions with local LLMs on a Mac Studio. Ollama plus Open WebUI setup, what local models can and cannot replace, and the real break-even math.
-
Your Mac Is a Local AI Supercomputer You're Using at 10% Capacity
How to run local LLMs on Apple Silicon with Ollama. Unified memory explained, which model size fits your RAM, realistic tokens per second on M-series Pro, Max, and Ultra chips, plus a 15-minute setup checklist.
-
Local LLMs with Ollama: Picking a local model for the specific task, not for the benchmark
A field-tested take on picking a local model for the specific task, not for the benchmark with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
Local LLMs with Ollama: Sunday-afternoon project: your own code reviewer that runs offline
A field-tested take on a Sunday-afternoon project: your own code reviewer that runs offline with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
