# Ollama v0.1.33 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.1.33
- **Released:** Apr 28, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.1.33/

## Executive Summary (TL;DR)
Ollama v0.1.33. Source highlight: Llama 3: a new model by Meta, and the most capable openly available LLM to date

## New Features
- `OLLAMA_NUM_PARALLEL`: Handle multiple requests simultaneously for a single model
- `OLLAMA_MAX_LOADED_MODELS`: Load multiple models simultaneously

## Improvements
- Qwen 110B: The first Qwen model over 100B parameters in size with outstanding performance in evaluations

## Bug Fixes
- Fixed issues where the model would not terminate, causing the API to hang.
- Fixed a series of out of memory errors on Apple Silicon Macs
- Fixed out of memory errors when running Mixtral architecture models