Bonsai-27B on recursive llama.cpp fork: full setup and real benchmark on RTX 3050
This third article about a recursive llama.cpp fork covers running the hybrid Bonsai-27B model (Delta-Net linear architecture) on a weak GPU, showing a real benchmark of depth D=0 vs D=12 on a cryptarithmetic task. With recurrence enabled (D=12), the model solved SEND+MORE=MONEY, while the base engine failed. Setup commands and recurrence environment variables are provided.
cubetitled-ui
Habr — хаб ИИ06.08 · 00:03