# Ollama 0.40.12-rc0 adds DFlash2 support

> Ollama’s pre-release adds DFlash2 support and updates MLX components, including a prompt-speed improvement for Gemma, Flint and Laguna.

Oossa · 2026-10-27 · https://oossa.com/en/ollama-0-40-12-rc0-adds-dflash2-support

Ollama has published version 0.40.12-rc0, a pre-release of its software for running AI models. The update adds DFlash2 support and includes an MLX version bump that Ollama says speeds up prompts for Gemma, Flint and Laguna.

It also changes how MLX handles small images for compact Gemma 4 vision towers, aiming to preserve detail, and updates its llama.cpp version to b11901.

## The facts

- The release is marked as a pre-release; its tag is v0.40.12-rc0.
- The changes include DFlash2 support and llama.cpp version b11901.

## Why it matters

People testing Ollama’s pre-release can try DFlash2 support and the listed MLX changes, but the release notes do not quantify speed gains or say when a stable release will arrive.

## Sources & references

1. [ollama/ollama v0.40.12](https://github.com/ollama/ollama/releases/tag/v0.40.12-rc0) – Ollama, 2026-10-27

Last updated: 2026-10-27