wici-ai/inferssd

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

1 best points · 0 comments · 1 Hacker News post · 362 GitHub stars · View on GitHub

Hacker News discussions

• Inferssd – Run models larger than RAM or VRAM by streaming MoE experts from SSD (1 points, 0 comments, by oceansky, 2026-10-30)