# llama.cpp release adds Nemotron‑3(.5)‑Embed support

> The open‑source llama.cpp library (v b11778) now runs Nemotron‑3(.5)‑Embed and ships binaries for macOS, iOS, Linux, Vulkan and CUDA.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-adds-nemotron-3-5-embed-support

ggml‑org released llama.cpp version b11778. The build adds support for the Nemotron‑3(.5)‑Embed model, a new text‑embedding model. It also ships pre‑compiled binaries for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu flavors, including Vulkan and CUDA‑12.8 GPU builds. The files are available via direct download links on the GitHub release page.

## The facts

- Adds Nemotron‑3(.5)‑Embed model support
- Release date: 2026‑10‑21

## Why it matters

Developers can now run Nemotron‑3(.5)‑Embed locally on a wide range of devices without needing a cloud service.

## Sources & references

1. [ggml-org/llama.cpp b11778](https://github.com/ggml-org/llama.cpp/releases/tag/b11778) – llama.cpp, 2026-10-21

Last updated: 2026-10-21