# Ollama v0.1.35 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.1.35
- **Released:** May 10, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.1.35/

## Executive Summary (TL;DR)
Ollama v0.1.35. Source highlight: Llama 3 ChatQA: A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

## New Features
- <kbd>Ctrl+J</kbd> characters will now properly add newlines in `ollama run`
- Added a new `done_reason` field in responses describing why generation stopped responding

## Bug Fixes
- Fixed issue where inference subprocesses wouldn't be cleaned up on shutdown.
- Fixed a series out of memory errors when loading models on multi-GPU systems
- Fixed issues when running `ollama show` for vision models
- Fixed issue where partially downloaded files wouldn't be cleaned up