# llama.cpp release adds Flint model and new binaries

> The open‑source llama.cpp library released version b11803 on Oct 22 2026, introducing the FlintForCausalLM model and pre‑built binaries for macOS, iOS, and Linux.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-adds-flint-model-and-new-binaries

The ggml‑org team published llama.cpp version b11803 on Oct 22 2026. The update adds a new FlintForCausalLM model, contributed with help from Codex. It also ships pre‑compiled binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds, including Vulkan‑enabled and CPU‑only variants.

## The facts

- Added FlintForCausalLM model (#30928).
- Binaries released for macOS arm64, macOS Intel, iOS, and Ubuntu x64/arm64/s390x.

## Why it matters

Developers can now run the new Flint model locally without building the code themselves, saving time on macOS and Linux setups.

## Sources & references

1. [ggml-org/llama.cpp b11803](https://github.com/ggml-org/llama.cpp/releases/tag/b11803) – llama.cpp, 2026-10-21

Last updated: 2026-10-21