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.
Liquid AI's LFM2.5: On-Device MoE With Tool Calling
Liquid AI dropped LFM2.5-8B-A1B on Hugging Face on May 28, the first reasoning-tuned MoE in the LFM2.5 family with 8.3B params, 1.5B active per token, and built-in tool calling.