# Ollama v0.11.5 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.11.5
- **Released:** Aug 15, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.11.5/

## Executive Summary (TL;DR)
Ollama v0.11.5. Source highlight: Performance improvements for the `gpt-oss` models

## Improvements
- Performance improvements for the `gpt-oss` models
- New memory management: this release of Ollama includes improved memory management for scheduling models on GPUs, leading to better VRAM utilization, model performance and less out of memory errors. These new memory estimations can be enabled with `OLLAMA_NEW_ESTIMATES=1 ollama serve` and will soon be enabled by default.
- Improved multi-GPU scheduling and reduced VRAM allocation when using more than 2 GPUs

## Bug Fixes
- Fix error when parsing bad harmony tool calls
- Fixed OpenAI-compatible API not supporting `reasoning_effort`