# llama.cpp 0.5 release adds Q5_0 and Q5_1 quantization support

> The open‑source LLM runner now handles two new 5‑bit formats and ships binaries for macOS, iOS and multiple Ubuntu platforms.

Oossa · 2026-11-13 · https://oossa.com/en/llama-cpp-0-5-release-adds-q5-0-and-q5-1-quantization-support

The ggml‑org team released llama.cpp version b12345. It adds support for Q5_0 and Q5_1 quantization, a 5‑bit compression that can speed up inference. The update also includes dedicated kernels for these formats on Hexagon devices. Pre‑built binaries are provided for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu builds, including CPU‑only and Vulkan variants.

## The facts

- Release version b12345 published on 2026‑11‑13
- Adds Q5_0 and Q5_1 quantization support

## Why it matters

Developers can run LLMs faster on low‑power hardware, expanding the range of devices that can host local AI models.

## Sources & references

1. [ggml-org/llama.cpp b12345](https://github.com/ggml-org/llama.cpp/releases/tag/b12345) – llama.cpp, 2026-11-13

Last updated: 2026-11-13