Ollama v0.40.15 — Release Notes & Engineering Impact

Source available — automated, not human-reviewed

Component: ollama · Channel: stable. Automated analysis, not a compatibility certification. How this works.

Analysis updated: 2026-11-06.

Compatibility not verified — check source notes

📄 .MD

✨ Features 6 ⚡ Improvements 1

⚡ Executive Summary (TL;DR)

Ollama v0.40.15 introduces native support for Xiaomi MiMo V2.6 and AutoTrust decision models, alongside CLI workflow updates and concurrency improvements for recurrent and vision GGUF models. These updates expand developer model choices and enhance multi-request serving performance.

Visit Ollama Official Site ↗ Official Release Source ↗ All Ollama Releases 📡 Ollama RSS

Who Does This Impact? (Role-Based Analysis)

💻 Software Engineers & Devs

You can now run Xiaomi MiMo V2.6 code and agent models as well as AutoTrust decision models locally via Ollama.

📊 Product & Engineering Leads

Feature velocity increases with the addition of new multi-size text and image decision models and improved integration with third-party tools like Claude Desktop and Pi.

⚙️ DevOps & Security

Recurrent and vision GGUF models now support concurrent request handling, improving local inference throughput.

✨ New Features & Capabilities (6)

Added support for Xiaomi MiMo V2.6 (9B) model for code and agent workflows
Added support for AutoTrust decision models (9b, 35b, and 27b-vl sizes) for text choices, probabilities, and ratings
ollama launch now supports Kimi Code CLI and migrates existing kimi-cli setups
ollama launch automatically populates Pi's model list and updates Claude Desktop's model picker with Ollama's actual model names
Added long-context (YaRN) scaling for Qwen3 and Qwen3.5 models
Running ollama with no arguments opens the welcome launcher

⚡ Performance & Enhancements (1)

Recurrent and vision GGUF models can now serve more than one request at a time

📄 View Raw Release Notes (Original Developer Log)

## MiMo V2.6 Xiaomi MiMo's [mimo-v2.6](https://ollama.com/library/mimo-v2.6), a 9B model built for code and agent workflows, is now supported in Ollama. ```sh ollama run mimo-v2.6 ``` ## AutoTrust decision models [AutoTrust](https://ollama.com/library/autotrust-jev) decision models read text and return choices, yes or no probabilities, and ratings for the questions you supply. The family includes 9b, 35b, and 27b-vl sizes — the 35b and 27b-vl sizes can also read images. ```sh ollama run autotrust-jev "A customer says their card was charged twice." --ask "Is this a billing issue?" ``` Note: autotrust-jev is supported on Apple silicon in this release. ## What's Changed - ollama launch now supports Kimi Code CLI — the successor to kimi-cli — and offers to migrate existing kimi-cli setups - ollama launch now fills in Pi's model list automatically so models can be picked inside Pi, and Claude Desktop's model picker shows Ollama's actual model names - Recurrent and vision GGUF models can now serve more than one request at a time - Qwen3 and Qwen3.5 models using long-context (YaRN) scaling - Running ollama with no arguments opens the welcome launcher **Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.14...v0.40.15

← Older Version Ollama v0.40.14-rc0 Newer Version → Ollama v0.40.15-rc2