# llama.cpp adds support for Kimi K3.1 vision model

> The open‑source LLM library llama.cpp now runs Kimi K3.1 vision on macOS, iOS and Linux.

Oossa · 2026-11-10 · https://oossa.com/en/llama-cpp-adds-support-for-kimi-k3-1-vision-model

The ggml‑org team released llama.cpp version b12259. It adds support for the Kimi K3.1 vision model and fixes preprocessing for K2.5 and K3.1. Pre‑built binaries are available for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds.

## The facts

- Release version b12259 on 2026‑11‑10
- Adds Kimi K3.1 vision support

## Why it matters

Developers can now run Kimi’s vision model locally on common desktop and mobile platforms without cloud services.

## Sources & references

1. [ggml-org/llama.cpp b12259](https://github.com/ggml-org/llama.cpp/releases/tag/b12259) – llama.cpp, 2026-11-10

Last updated: 2026-11-10