April 2026 TLDR setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive
- Mac mini with Apple Silicon (M1/M2/M3/M4/M5)
- At least 16GB unified memory for Gemma 4 (default 8B)
- macOS with Homebrew installed
April 2026 TLDR setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive
| # Clone llama.cpp | |
| git clone https://github.com/ggerganov/llama.cpp.git | |
| cd llama.cpp | |
| # Build it | |
| make clean | |
| LLAMA_METAL=1 make | |
| # Download model | |
| export MODEL=llama-2-13b-chat.ggmlv3.q4_0.bin |
| FROM hayd/alpine-deno:1.10.1 | |
| WORKDIR /src/app | |
| ADD deps.ts ./ | |
| RUN ["deno", "cache", "deps.ts"] | |
| ADD *.ts ./ | |
| RUN ["deno", "cache", "mod.ts"] | |
| ENTRYPOINT ["deno", "run", "--unstable", "--allow-net", "--allow-hrtime", "--allow-env", "--cached-only", "--no-check", "mod.ts"] |
NOTE: Time flies, and it's been almost five years(!) since I wrote this. Beaware the text below is now outdated (e.g., now Asahi Linux has graphics acceleration even better than this). The commands listed are up-to-date.
I bought M1 MacBook Air. It is the fastest computer I have, and I have been a GNOME/GNU/Linux user for long time. It is obvious conclusion that I need practical Linux desktop environment on Apple Silicon.
| package main | |
| import ( | |
| "context" | |
| "flag" | |
| "fmt" | |
| "log" | |
| "net/http" | |
| "os" | |
| "os/signal" |