# llama.cpp vb12387 adds 32‑bit fix and new binaries

> The open‑source Llama inference library releases version b12387 with a 32‑bit bug fix and binaries for macOS, iOS and various Ubuntu builds.

Oossa · 2026-11-14 · https://oossa.com/en/llama-cpp-vb12387-adds-32-bit-fix-and-new-binaries

ggml‑org released llama.cpp version b12387 on 2026‑11‑14. The update fixes a ctz64 bug on 32‑bit systems. It also provides pre‑built binaries for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu flavours including x64, arm64 and s390x, with optional Vulkan and zDNN support.

## The facts

- Fixes ctz64 on 32‑bit (#32273)
- Binaries for macOS Intel (x64) and Ubuntu x64, arm64, s390x released

## Why it matters

The fix lets developers running 32‑bit hardware use llama.cpp reliably, and the new binaries simplify setup on common desktop and server platforms.

## Sources & references

1. [ggml-org/llama.cpp b12387](https://github.com/ggml-org/llama.cpp/releases/tag/b12387) – llama.cpp, 2026-11-14

Last updated: 2026-11-14