# llama.cpp release b11713 adds faster low‑bit CUDA support

> The open‑source llama.cpp library released version b11713 on Oct 17, 2026, with speed‑up for low‑bit matrix‑vector ops on CUDA GPUs and new binary builds.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-release-b11713-adds-faster-low-bit-cuda-support

The ggml‑org team published llama.cpp version b11713 on Oct 17, 2026. The update improves CUDA performance for low‑bit types by using a faster MMVQ algorithm. It also adds a small fix for HIP (AMD) GPUs on Q3_K and Q6_K quantizations. Pre‑built binaries for macOS, iOS, and several Ubuntu targets (CPU, Vulkan, CUDA) are now available for download.

## The facts

- Release date: Oct 17, 2026 ("Sat Oct 17 2026 18:00:52 GMT+0200")
- Adds faster CUDA MMVQ for low‑bit types (#30517)

## Why it matters

Developers can run quantized LLMs on NVIDIA GPUs more quickly, lowering inference costs for local AI applications.

## Sources & references

1. [ggml-org/llama.cpp b11713](https://github.com/ggml-org/llama.cpp/releases/tag/b11713) – llama.cpp, 2026-10-17

Last updated: 2026-10-17