OllamaReleasedpatch

Ollama 0.40.7 is out: highlights and upgrade guide

By VersionUpdates Editorial · Published Oct 18, 2026 · 2 min read

At a glance

Ollama 0.40.7 is a patch release published on Oct 18, 2026. It follows Ollama 0.40.6 by 2 days. It includes 8 listed changes.

pplx-decider is a 27B decision model from Perplexity, fine-tuned from
Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without
Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open
Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing
ollama show now reports which renderer and parser a model uses and where its chat template comes from; the API

This is a patch release, normally bug fixes only. It is usually safe to upgrade after your tests pass.

Linux

curl -fsSL https://ollama.com/install.sh | sh

macOS / Windows

Download the installer from ollama.com/download

pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B
Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items
Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open reasoning items, producing misordered/duplicate tool call events
Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing to run
ollama show now reports which renderer and parser a model uses and where its chat template comes from; the API exposes the same values in new renderer, parser, and template_source fields
More draft models now work with speculative decoding: llama-server infers the draft type automatically instead of requiring Ollama to identify it
ollama launch claude now clamps CLAUDE_CODE_AUTO_COMPACT_WINDOW to Claude Code's supported range, avoiding a "window too large" warning
Updated llama.cpp and MLX

When was Ollama 0.40.7 released?

Ollama 0.40.7 was published on Oct 18, 2026.

Is Ollama 0.40.7 a major update?

No. It is a patch release, mainly bug fixes.

How do I upgrade to Ollama 0.40.7?

Use the commands in the “How to upgrade” section, then run your test suite.

Where are the official Ollama 0.40.7 notes?

On the project's official release page: https://github.com/ollama/ollama/releases/tag/v0.40.7