DesktopFly brings FlyWire’s connectome data to life on macOS: a 668-neuron spiking (LIF) circuit turns cursor-driven looming inputs into giant-fiber spikes, then into embodied behavior like walking, grooming, and escape. Learn how real wiring becomes real-time motion.
Swiftlet demonstrates how to run Qwen MoE models locally by keeping only the dense core in RAM and streaming routed experts from SSD on demand. It reports ~4.3GB RAM for a 4-bit 80B model on an M5 Mac, and an on-device 35B experience on iPhone around ~2.5GB RAM.
TurboFieldfare runs Gemma 4 26B-A4B on Apple Silicon with ~2GB RAM by keeping core weights + an FP16 KV cache resident and streaming only the routed MoE experts from SSD. This post explains the memory pieces (MoE routing, KV cache, quantization) and walks through building, installing, and tuning the runtime.