Notes on brands, websites and growth

Practical guides on how things work, what to choose and how to get found.

Cover: a 2019 16-inch MacBook Pro keyboard in a circle beside the Ollama and Qwen marks, labelled MacBook Pro 2019, Core i9, 32 GB

Can a 2019 Intel MacBook Pro Run a Free Local AI Coding Assistant?

Before installing AI models and coding agents, check what an older Intel Mac can handle, and which GPU claims still need proof on your own machine.

Browse all

Episodes

Cover: a shop owner checking an order on her phone among packed parcels, beside three steps, product page, checkout and delivery, and the line 40% leave over extra costs

Business Online Foundations

3 Episodes

Cover: a team working at laptops in an office beside a laptop sticker and the post’s checklist, business line, 3-year spec and Windows 11 Pro, with the spec 14-inch, 16 GB, 512 GB

Buying and Making for Business

3 Episodes

Local AI on an Intel Mac: Tested and Analysed

10 Episodes

Articles

Cover: shop photos of a cap, mug, tee, hoodie and apron growing in size, a Sanity image address, and Vercel handing the resizing down to Sanity in a panel of its own

Websites & Apps

Vercel’s free image limit: serving Next.js pictures from Sanity

Vercel’s free Hobby plan includes 5,000 image transformations a month, and image-heavy sites reach it fast. A short Next.js loader hands every resize to Sanity’s image CDN instead.

Cover: the Vercel, Next.js and Sanity marks beside a wall of stored pages with one page refreshing under its tag

Websites & Apps

Vercel’s free ISR writes: rebuilding only what changed

Vercel’s free Hobby plan allows 200,000 ISR write units over a rolling 30 days, and an hourly refresh of busy pages can pass it. Cache tags and Sanity’s publish webhook rebuild only the pages a change touches.

Cover: an 8 GB ceiling over the Qwen mark and the names Gemma 4 and Granite 4.2, beside memory plans where two settings pass the limit and flash attention brings them under

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 10/10

After the Reboot: Five Local Models, One Context Setting and an 8 GB Ceiling

A full restart, then every command checked again: Qwen 3.5, Granite 4.2, Ministral 3 and Gemma 4 on a 2019 MacBook Pro's Radeon Pro 5500M. The command layer came back intact; the 8 GB card, one model's packaging and the Mac's thermal cap decided the rest.

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 1/10

Can a 2019 Intel MacBook Pro Run a Free Local AI Coding Assistant?

Before installing AI models and coding agents, check what an older Intel Mac can handle, and which GPU claims still need proof on your own machine.

Cover: the Ollama and Qwen marks beside the Ollama prompt box, Kilo Code’s Review First card and a Hello World page, with the command ollama run qwen3.5:4b

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 2/10

Install Ollama and Qwen

Kilo Code, Twinny and Claude Code against a local Ollama server on an Intel Mac: a working API, a real generated webpage, and the limits small models hit when they drive coding agents.

Cover: the Ollama, Qwen and Python marks over the qwen3.5 4B and 9B rows of Ollama’s model table, and a download bar that breaks at 48% and resumes to 100%

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 3/10

Recover an Interrupted Ollama Model Download: Qwen 9B, unexpected EOF, and a Better Resume Strategy

A practical recovery guide for interrupted Qwen downloads, from unexpected EOF failures at 48% and 91% to safe retries, resumable transfers, integrity checks, and final Ollama verification.

Cover: the chain from llama.cpp through Vulkan and MoltenVK to the Radeon Pro 5500M, beside the llama.cpp banner from llama-cli

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 4/10

Run Local LLMs on an Intel Mac's AMD Radeon GPU with Vulkan, MoltenVK, and llama.cpp

Ollama ran Qwen on the CPU of a 2019 Intel MacBook Pro. A Vulkan-enabled llama.cpp build finally put the machine's Radeon Pro 5500M to work, with verified device detection and model offloading.

Cover: the Qwen mark and a graphics card beside the prompt processing and generation charts for Qwen 3.5 4B and 9B on the Radeon

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 5/10

AMD Radeon Pro 5500M LLM Benchmarks: Qwen 4B vs. 9B with llama.cpp and Vulkan

Measured Qwen3.5 4B and 9B performance on a 2019 Intel MacBook Pro after Vulkan and MoltenVK enabled its Radeon Pro 5500M, with commands, offloading evidence, and honest limits.

Cover: the llama.cpp and bash marks and the word Vulkan over a pattern of folders, beside four steps of the move: Copy, Rebuild, Launch and Review

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 6/10

Make a Local AI Installation Permanent: Organise llama.cpp, Rebuild Vulkan, and Reuse Ollama Models

Move a working llama.cpp experiment out of Downloads, rebuild Vulkan cleanly, reuse existing Ollama Qwen weights, and create a permanent launch workflow on an Intel Mac.

Cover: OpenCode taking the request to find the homepage button, the built-in tools menu of llama.cpp’s web chat, the OpenCode, llama.cpp and Qwen marks and an offline sign

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 7/10

Build an Offline Coding Agent with OpenCode and llama.cpp on an Intel Mac

Connect OpenCode 2.1.2 to a Radeon-backed local Qwen 9B server, configure approval-driven tools, recover from an 8K context failure, and verify project file access at 32K.

Cover: four steps, read, write, approve and run, over the agent’s hello.js code and its output 5, with the OpenCode, Node.js and JavaScript marks

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 8/10

Testing a Local AI Coding Agent: Read, Write, Approve, Execute

A real OpenCode test in which Qwen 9B read project configuration, created hello.js after approval, executed it through Node.js, and correctly reported the output 5.

Cover: a timer reading 8:19 over the agent’s Fibonacci output ending in runs of zeros and its letters turning to asterisks, with the Qwen and OpenCode marks

Local AI on an Intel Mac: Tested and Analysed

AI & AutomationEP 9/10

Eight Minutes for Wrong Answers: How to Evaluate a Small Local AI Coding Agent

A Qwen 9B agent completed a Fibonacci task in 8 minutes 19 seconds, but ordinary JavaScript Number arithmetic corrupted large integers. The failure shows how to test coding agents for correctness.

Business Online Foundations

Websites & AppsEP 1/3

Selling online: what an online store needs

Product pages, a checkout that shows the total early, delivery customers can follow and the trust signals that turn visits into orders.

Buying and Making for Business

Equipments & SuppliesEP 1/3

Buying office laptops in bulk: what to check

Business line over consumer line, the spec that lasts three years, Windows 11 Pro, the warranty that matters and a rollout that keeps every desk the same.