Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: local-llm
Local AI for Confidential Documents: What to Run on Your Own Hardware
Keeping contracts, payroll and audit files off cloud APIs: which pipeline stages must be local, what hardware fits, where local models are weaker, and costs.
3 min readHow Much Memory Do You Need for Local AI? Speeds from 16 GB to 512 GB
Measured local LLM speed and quality across 16, 32, 128, 256 and 512 GB machines, what each class can run, and which GPUs, Macs and mini PCs fit where.
5 min readMac Studio M5 Ultra vs DGX Spark: Local LLM Speed on the Same Models
Mac Studio M5 Ultra 256 GB against one, two and four DGX Spark boxes on Nemotron, Qwen3.8 and DeepSeek-V4.1-Flash: decode, prefill, batching and images.
4 min readRTX 5090 Local LLM Benchmarks: Same Qwen3.8-27B, 67 to 253 Tokens per Second
Qwen3.8-27B on one RTX 5090 across TensorFold, NInfer, ExLlamaV3, Qwentin and vLLM: decode, prefill, parallel throughput, quality and which stack to run.
4 min readRTX 5060 Ti 16 GB for Local AI: Measured LLM, Image and Speech Speeds
RTX 5060 Ti 16 GB tested for local AI: five LLMs from 42 to 116 tok/s, first-token times at 32K, image, video, 3D and speech speeds, and what to run on it.
6 min readTensorFold vs llama.cpp on a Mac Studio M5 Ultra: 1.84x the Throughput on Real JSON Work
I benchmarked TensorFold 1.2.0 against llama.cpp on a Mac Studio M5 Ultra with Qwen3.8-27B and 80 real JSON requests: 1.84x throughput at 8 concurrent.
9 min readHy-MT2-7B on Five Local Runtimes: Which One Should Serve Translation on a Mac?
Hy-MT2-7B load-tested on llama.cpp, LM Studio, mlx-lm, Ollama and MLX-Serve on two Mac Studio M5 Ultra machines: throughput, scaling, determinism, memory.
9 min readA Local LLM Agent Workflow Built From Folders and Markdown Files
Build a gated, multi-stage local agent pipeline where each stage is a folder, prompts are editable markdown, and a human reviews output before the costly step.
25 min readWire LM Studio to MCP Servers for Files, GitHub and a Browser
Step-by-step mcp.json configs that let a local model use the filesystem, GitHub OAuth tools and Playwright, with model picks and fixes for common errors.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.