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
| # Taken from https://johanwind.github.io/2023/03/23/rwkv_details.html. | |
| # I've added additional comments restructured it a tiny bit, which makes it clearer for me. | |
| import numpy as np | |
| from torch import load as torch_load # Only for loading the model weights | |
| from tokenizers import Tokenizer | |
| exp = np.exp | |
| layer_norm = lambda x, w, b : (x - np.mean(x)) / np.std(x) * w + b | |
| sigmoid = lambda x : 1/(1 + exp(-x)) |
| #!/usr/bin/env python3 | |
| import argparse | |
| import glob | |
| import os | |
| import struct | |
| import sys | |
| from sentencepiece import SentencePieceProcessor | |
| HPARAMS = keys = ["vocab_size", "dim", "multiple_of", "n_heads", "n_layers"] |
| # Cross toolchain configuration for using clang-cl. | |
| set(CMAKE_SYSTEM_NAME Windows) | |
| set(CMAKE_SYSTEM_VERSION 10.0) | |
| set(CMAKE_SYSTEM_PROCESSOR AMD64) | |
| set(CMAKE_C_COMPILER "/usr/bin/clang-cl-9") | |
| set(CMAKE_CXX_COMPILER "/usr/bin/clang-cl-9") | |
| set(CMAKE_LINKER "/usr/bin/lld-link-9") |
Ever wanted to delete all your likes/favorites from Twitter but only found broken/expensive tools? You are in the right place.
setInterval(() => {
for (const d of document.querySelectorAll('div[data-testid="unlike"]')) {
d.click()
}| /************* | |
| * ambush.js * | |
| ************* | |
| * | |
| * Oh. Oh, I see. This wasn't quite part of the plan. | |
| * | |
| * Looks like they won't let you take the Algorithm | |
| * without a fight. You'll need to carefully weave your | |
| * way through the guard drones. | |
| * |
| /********************** | |
| * fordingTheRiver.js * | |
| ********************** | |
| * | |
| * And there's the river. Fortunately, I was prepared for this. | |
| * See the raft on the other side? | |
| * | |
| * Everything is going according to plan. | |
| */ |
| /******************* | |
| * intoTheWoods.js * | |
| ******************* | |
| * | |
| * Ah, you're out of the woods now. Or into the woods, as the | |
| * case may be. | |
| * | |
| * So take a deep breath, relax, and remember what you're here | |
| * for in the first place. | |
| * |
| /****************** | |
| * minesweeper.js * | |
| ****************** | |
| * | |
| * So much for Asimov's Laws. They're actually trying to kill | |
| * you now. Not to be alarmist, but the floor is littered | |
| * with mines. Rushing for the exit blindly may be unwise. | |
| * I need you alive, after all. | |
| * | |
| * If only there was some way you could track the positions |
| /**************** | |
| * drones101.js * | |
| **************** | |
| * | |
| * Do you remember, my dear Professor, a certain introductory | |
| * computational rationality class you taught long ago? Assignment | |
| * #2, behavior functions of autonomous agents? I remember that one | |
| * fondly - but attack drones are so much easier to reason about | |
| * when they're not staring you in the face, I would imagine! |