# Ollama v0.40.12 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.40.12
- **Released:** Oct 27, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.40.12/

## Executive Summary (TL;DR)
v0.40.12 adds the LFM3 family of small multimodal models and d1 2B decision models, expanding local AI capabilities on Apple silicon. It also delivers performance improvements and bug fixes without introducing breaking changes.

## New Features
- LFM3 family (lfm3, lfm3-vl, lfm3-audio, lfm3-omni) introducing text, image, audio, and multimodal small models for local agents
- d1 2B decision models (d1, d1-omni) adding audio-enabled text and image decision capabilities
- ollama launch support for OpenCode v2

## Improvements
- Faster prompt processing on Apple silicon for Gemma 4, Flint and Laguna models
- Speculative decoding now supports DFlash2 draft models on MLX
- Gemma 4 retains more detail in small images
- Updated MLX and llama.cpp libraries

## Bug Fixes
- Fixed tool-only assistant turn issue in Kimi CLI