# llama.cpp v0.1.77 release adds memory‑leak fixes and new binaries

> The open‑source LLM runtime llama.cpp released version b11277 on Sep 30 2026, fixing buffer reset bugs and providing fresh macOS, iOS, and Ubuntu builds.

Oossa · 2026-09-30 · https://oossa.com/en/llama-cpp-v0-1-77-release-adds-memory-leak-fixes-and-new-binaries

Produced and translated with AI assistance. Check the original sources below.

The ggml‑org team published llama.cpp release b11277. It patches a buffer‑reset issue that caused memory leaks. The update also ships pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu flavors, including Vulkan and CUDA GPU options. Users can download the files directly from the release page.

## The facts

- Release version b11277 published on Sep 30 2026
- Includes new binaries for macOS, iOS, Ubuntu x64/arm64, Vulkan and CUDA 12

## Why it matters

Fixing the leak improves stability for developers running LLMs locally, and the ready‑made binaries make it easier to try llama.cpp on more platforms.

## Sources & references

1. [ggml-org/llama.cpp b11277](https://github.com/ggml-org/llama.cpp/releases/tag/b11277) – llama.cpp, 2026-09-30

Last updated: 2026-09-30