# Ollama v0.3.7 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.3.7
- **Released:** Aug 20, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.3.7/

## Executive Summary (TL;DR)
Ollama v0.3.7. Source highlight: Hermes 3: Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research, which includes support for tool calling.

## Improvements
- Phi 3.5: A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.
- CUDA 12 support: improving performance by up to 10% on newer NVIDIA GPUs
- Improved performance of `ollama pull` and `ollama push` on slower connections

## Bug Fixes
- Fixed issue where setting `OLLAMA_NUM_PARALLEL` would cause models to be reloaded on lower VRAM systems