b9436

B9436 is an intermediate build release of llama.cpp, the open-source C/C++ implementation for running large language model inference on consumer hardware. This build typically includes updates to model architecture support, performance optimizations, or bug fixes in the underlying ggml tensor library. Developers use intermediate build numbers like b9436 to access new features or improvements before official stable releases.

Source: llama.cpp Releases | 2026-05-30