NVIDIA's DGX Spark 64GB starts at $4,999 on October 23, while the 128GB model is now $6,950. We summed the real Hugging Face file sizes of 16 local LLM, image and video setups: 8 fit in 64GB, 8 don't, including gpt-oss-120b and NVIDIA's own Nemotron 3 Super.
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 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.