Swiftlet: Run an 80B Qwen Locally on a Mac or iPhone
Swiftlet runs the real Qwen3-Next-80B on a Mac in 4.3 GB of RAM and a 35B model on an iPhone, using expert streaming to keep only active experts in memory.
Swiftlet runs the real Qwen3-Next-80B on a Mac in 4.3 GB of RAM and a 35B model on an iPhone, using expert streaming to keep only active experts in memory.