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: apple-silicon
Mac 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 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 readRunning Local Coding Agents on a Mac With oMLX: Disk-Backed KV Cache Explained
oMLX caches prompt prefixes on SSD so local coding agents stay fast on Apple Silicon. Install it and connect Claude Code, Codex, Cursor and OpenCode to it.
9 min readPrivate Multimodal RAG on an M1 Mac: Selective Chart Reading With Ollama
Private multimodal RAG on an M1 Mac with Ollama: PyMuPDF for text and tables, a small Qwen vision model only for charts, number checks and ChromaDB retrieval.
10 min readRunning AI Agents on a MacBook: Why oMLX Beats Raw MLX
Raw MLX needed about 20 seconds for an 8.7k-token agent context on an M1 Max. oMLX cut it to roughly 3 with batching and a tiered KV cache. Numbers and why.
5 min readRun Local LLMs on a Mac With MLX Instead of the Default llama.cpp Engine
When Apple's MLX beats llama.cpp for a local LLM on Apple Silicon, with speed ranges by model size, three ways to switch from Ollama, and pitfalls to avoid.
5 min readRun Qwen3.8-Flash-Next on a 64GB MacBook: Files, Quants and llama.cpp Flags
Run a 180B-parameter MoE on an M4 Max or M1 Max with no CPU offload: which GGUF to pick, how the n-gram table is split into shards, and the exact llama-server command.
9 min readFrom Fine-Tuning to Precision: Significantly Reducing
Fine tuning plus RAG to cut hallucinations: why fine tuning alone falls short, the architecture with Ollama, and how precision improved on a narrow domain.
13 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.